© 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. 129143
    Prev
    Next
    INDEX
    Explanations

    wearing a

    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
    拏
    -1.77
    didn
    -1.63
     GARANT
    -1.61
     preuves
    -1.58
    嚎
    -1.58
    眎
    -1.55
    他的
    -1.55
     .(
    -1.49
     mauva
    -1.48
    vailable
    -1.47
    POSITIVE LOGITS
     by
    1.73
     or
    1.69
     using
    1.63
    From
    1.46
     of
    1.46
     dengan
    1.42
     WITH
    1.41
    同樣
    1.41
    Some
    1.40
    Two
    1.40
    Activations Density 0.009%

    No Known Activations