© 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. 22-GEMMASCOPE-RES-131K
    7. 54349
    Prev
    Next
    INDEX
    Explanations

    code comments or structure markers

    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_22/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
    <bos>
    -1.70
    香りが
    -1.63
    𓍊
    -1.63
     Grüßen
    -1.63
    があります
    -1.62
    鼍
    -1.61
    や
    -1.61
    縠
    -1.59
    脔
    -1.47
    がある
    -1.46
    POSITIVE LOGITS
     and
    2.28
     or
    2.03
     of
    2.02
    際は
    1.83
    際には
    1.70
    為に
    1.63
    の方に
    1.57
    ときの
    1.55
    際の
    1.55
     with
    1.55
    Activations Density 0.012%

    No Known Activations