© 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. 84343
    Prev
    Next
    INDEX
    Explanations

    abstract heading

    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
    -2.22
     who
    -1.88
     and
    -1.68
     your
    -1.64
     not
    -1.60
    と呼ば
    -1.45
     και
    -1.42
     which
    -1.38
    摇了
    -1.37
     see
    -1.32
    POSITIVE LOGITS
    demás
    1.60
    一愣
    1.57
    總是
    1.55
    不夠
    1.50
    
    1.49
     uscita
    1.48
     هاي
    1.47
     Какой
    1.43
     verwendeten
    1.41
     größe
    1.40
    Activations Density 0.160%

    No Known Activations