© 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. 166
    Prev
    Next
    INDEX
    Explanations

    at followed by articles

    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
     the
    -2.38
     gröss
    -1.77
    n
    -1.74
    to
    -1.68
    at
    -1.68
    We
    -1.64
    according
    -1.63
    2
    -1.63
    in
    -1.62
    from
    -1.61
    POSITIVE LOGITS
     "
    1.73
    倥
    1.73
     scène
    1.65
     animés
    1.64
     enfants
    1.63
     also
    1.62
     carcasa
    1.56
     élevés
    1.53
    ského
    1.52
    簟
    1.52
    Activations Density 0.008%

    No Known Activations