© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66974
    Prev
    Next
    INDEX
    Explanations

    language followed by language name

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

    This neuron primarily detects occurrences of the word “language” (including its plural form “languages”) across different contexts.

    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
    栳
    -3.19
    釙
    -2.92
    ﮏ
    -2.80
    ⭓
    -2.75
    koszulka
    -2.75
    盌
    -2.64
    媪
    -2.63
    孥
    -2.55
     什么
    -2.53
    錞
    -2.53
    POSITIVE LOGITS
    .
    3.36
    </td>
    3.08
    man
    2.94
    m
    2.89
    </h5>
    2.86
    b
    2.69
    in
    2.56
     of
    2.53
    hi
    2.47
     vollständ
    2.45
    Activations Density 0.017%

    No Known Activations