© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61398
    Prev
    Next
    INDEX
    Explanations

    place names and regions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron predominantly activates on proper names of geographic locations (e.g., cities, regions, rivers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    proper nouns for specific geographic entities (towns, districts, regions, rivers, wards, and related place identifiers).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    place names, particularly towns and geographic locations in the UK and Eastern Europe.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    KommentareTeilen
    -1.63
    ć
    -1.57
     dijo
    -1.55
                
    -1.52
    diol
    -1.52
     ),
    -1.48
    —
    -1.45
    ₤
    -1.43
    нию
    -1.41
    <td>
    -1.41
    POSITIVE LOGITS
    ↵↵
    1.57
     spesielt
    1.53
     educativas
    1.46
     större
    1.43
     sincero
    1.42
    deckung
    1.41
     valgt
    1.41
     personalizadas
    1.41
    下一个
    1.41
     qualities
    1.41
    Activations Density 0.826%

    No Known Activations