© 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. 105302
    Prev
    Next
    INDEX
    Explanations

    force to be reckoned with

    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
     aktiviert
    -1.65
     científicos
    -1.63
     profundos
    -1.56
     europeos
    -1.55
     significativos
    -1.52
     belangrijke
    -1.51
    otros
    -1.50
     extranjeros
    -1.50
     others
    -1.49
     españoles
    -1.48
    POSITIVE LOGITS
     як
    1.80
     in
    1.63
    клю
    1.59
    >
    1.55
     It
    1.53
     and
    1.48
    所以在
    1.48
    但是在
    1.43
    而且
    1.33
     explicar
    1.32
    Activations Density 0.008%

    No Known Activations