© 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. 130414
    Prev
    Next
    INDEX
    Explanations

    on followed by the

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     and
    -2.52
     "
    -1.74
    atchewan
    -1.59
    <bos>
    -1.59
     noteworthy
    -1.57
    amını
    -1.52
     venganza
    -1.52
    forKey
    -1.50
     ingrained
    -1.48
     seemingly
    -1.47
    POSITIVE LOGITS
    from
    1.80
     of
    1.67
    locene
    1.64
     certaines
    1.56
     the
    1.54
     our
    1.52
     troisième
    1.52
     visse
    1.50
    isés
    1.49
     ハーフ
    1.45
    Activations Density 0.044%

    No Known Activations