© 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. 66403
    Prev
    Next
    INDEX
    Explanations

    over the past years

    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
    いら
    -2.38
     など
    -2.23
     râ
    -2.19
     preocupado
    -2.11
    \
    -1.95
     evitando
    -1.94
     is
    -1.93
     ott
    -1.91
     ofrecemos
    -1.90
     comprando
    -1.88
    POSITIVE LOGITS
    錞
    2.45
    CHREIBUNG
    2.31
     unsere
    2.13
     stupidity
    2.13
     majority
    2.13
    鬟
    2.09
     meyd
    2.06
     mundiales
    2.06
     years
    2.05
     commenti
    2.05
    Activations Density 0.021%

    No Known Activations