© 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. 67370
    Prev
    Next
    INDEX
    Explanations

    HTML tags and code

    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
     to
    -1.87
     this
    -1.80
     then
    -1.64
     sometimes
    -1.58
     both
    -1.57
    しばらく
    -1.51
    s
    -1.50
     whose
    -1.48
     these
    -1.47
     not
    -1.46
    POSITIVE LOGITS
    荩
    2.14
    Ꮸ
    1.95
    ࿊
    1.83
    鈇
    1.78
    鴣
    1.77
    튤
    1.74
     नाम
    1.73
    玏
    1.73
    쥘
    1.70
    ープン
    1.69
    Activations Density 0.009%

    No Known Activations