© 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. 128038
    Prev
    Next
    INDEX
    Explanations

    .com, .org, .us, TLDs

    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
     mostrando
    -1.90
    蛲
    -1.83
    XXXXX
    -1.81
    various
    -1.75
     passt
    -1.73
     they
    -1.73
     plusieurs
    -1.67
     siè
    -1.66
     Não
    -1.66
    を取る
    -1.66
    POSITIVE LOGITS
     all
    2.69
     or
    2.38
     definitely
    2.33
     at
    2.20
     on
    2.19
     any
    2.17
     certainly
    2.08
     every
    2.00
     usually
    2.00
     in
    1.99
    Activations Density 0.103%

    No Known Activations