© 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. 10-GEMMASCOPE-RES-131K
    7. 102315
    Prev
    Next
    INDEX
    Explanations

    link rel="author" or stylesheet

    np_acts-logits-general · gemini-2.5-flash-lite

    the `rel` attribute in HTML link tags.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    In
    -1.94
     utiliser
    -1.88
     wondrous
    -1.86
     uniquement
    -1.84
     Allows
    -1.81
    ⟣
    -1.81
     пять
    -1.80
     doivent
    -1.80
     gekauft
    -1.76
    [
    -1.71
    POSITIVE LOGITS
     at
    2.52
     of
    2.27
     on
    2.06
     through
    1.91
     since
    1.91
     that
    1.87
     also
    1.79
    ))$_
    1.66
    ㈣
    1.65
    زارش
    1.63
    Activations Density 0.008%

    No Known Activations