© 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. 22-GEMMASCOPE-RES-131K
    7. 130133
    Prev
    Next
    INDEX
    Explanations

    address of variable

    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>
    -1.67
    なども
    -1.65
    などを
    -1.63
     岁
    -1.60
    などは
    -1.59
    と
    -1.57
    了一会儿
    -1.53
     to
    -1.53
     elección
    -1.51
    ೢ
    -1.49
    POSITIVE LOGITS
     the
    1.95
    ＊＊＊＊
    1.95
    ところに
    1.86
    ＊＊＊
    1.84
    為に
    1.70
    感じで
    1.68
    際には
    1.62
    つづく
    1.58
     zapatillas
    1.56
     alimenti
    1.56
    Activations Density 0.002%

    No Known Activations