© 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. 19551
    Prev
    Next
    INDEX
    Explanations

    util. and util;

    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
     from
    -1.69
     by
    -1.27
    B
    -1.13
     B
    -1.12
     and
    -1.09
     may
    -1.09
     +
    -1.08
    monix
    -1.05
     during
    -1.05
     any
    -1.04
    POSITIVE LOGITS
     entanto
    1.45
    が少ない
    1.42
    куртка
    1.41
     annonces
    1.38
     味噌
    1.34
     problèmes
    1.34
     paille
    1.32
    ureusement
    1.31
     jaula
    1.30
     ー
    1.27
    Activations Density 0.217%

    No Known Activations