© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3738
    Prev
    Next
    INDEX
    Explanations

    Osaka POI locations and universities

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

    The neuron fires on multi‐letter uppercase tokens (i.e. technical acronyms or abbreviations such as POI, API, HSSF, NPOI).

    oai_token-act-pair · o4-miniTriggered 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
    ).
    -3.19
    .”
    -2.77
    });
    -2.50
    ୌ
    -2.50
    屜
    -2.48
    .“
    -2.38
     '');
    -2.34
    ти
    -2.34
    "]);
    
    -2.30
     другой
    -2.28
    POSITIVE LOGITS
    {
    2.98
    みると
    2.50
     mauva
    2.41
     What
    2.39
     spearheaded
    2.34
     Что
    2.34
    enced
    2.31
    '
    2.31
    having
    2.30
    ⠜
    2.30
    Activations Density 0.002%

    No Known Activations