© 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. 66672
    Prev
    Next
    INDEX
    Explanations

    home page components

    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
    -1.89
     अलावा
    -1.60
     což
    -1.43
    胤
    -1.41
     ktoré
    -1.37
     originalmente
    -1.36
     considerada
    -1.35
    (;;)
    -1.33
     هناك
    -1.33
    </i>
    -1.33
    POSITIVE LOGITS
     appartements
    1.68
    ଃ
    1.64
     almofada
    1.60
     paillettes
    1.59
     bougies
    1.55
     toalha
    1.54
    千萬
    1.54
    與
    1.52
    總是
    1.52
     Funda
    1.51
    Activations Density 0.006%

    No Known Activations