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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111514
    Prev
    Next
    INDEX
    Explanations

    financial or property terms

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

    The neuron fires strongly on individual content words (nouns or verbs) that carry the core meaning of a sentence, filtering out function words.

    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
     masaj
    -1.75
     sopa
    -1.66
    榖
    -1.58
     蕾
    -1.52
    dores
    -1.52
     vecin
    -1.51
     tambor
    -1.51
    笮
    -1.50
     pijama
    -1.49
    綃
    -1.49
    POSITIVE LOGITS
    ↵↵
    1.95
     is
    1.65
     recibió
    1.61
    readFileSync
    1.56
     zarówno
    1.48
    BURGH
    1.48
     they
    1.48
     partenza
    1.47
     its
    1.41
    
    1.38
    Activations Density 0.067%

    No Known Activations