© 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. 60853
    Prev
    Next
    INDEX
    Explanations

    top of

    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
     then
    -1.77
    ☺☺
    -1.69
     ??????
    -1.65
    shank
    -1.63
    蠖
    -1.58
    *);
    -1.57
    以外の
    -1.52
    这一
    -1.51
    JOUR
    -1.49
     eerst
    -1.48
    POSITIVE LOGITS
     даже
    1.74
     of
    1.63
    o
    1.60
     incluso
    1.57
     sogar
    1.48
    3
    1.46
     при
    1.45
     fordern
    1.41
     joka
    1.41
     todas
    1.40
    Activations Density 0.037%

    No Known Activations