© 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. 40132
    Prev
    Next
    INDEX
    Explanations

    extremely [adjective]

    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
    入れて
    -1.58
     acusa
    -1.52
    书房
    -1.43
     unable
    -1.41
    ").
    -1.39
    ()).
    -1.38
    RTHOOK
    -1.38
     bliss
    -1.38
    ৢ
    -1.36
    НОСТИ
    -1.34
    POSITIVE LOGITS
     and
    2.00
     vorige
    1.52
    无比
    1.46
     bébés
    1.43
     kogo
    1.43
     but
    1.41
    疍
    1.41
     mogli
    1.39
     voorbeeld
    1.37
    并且
    1.34
    Activations Density 0.029%

    No Known Activations