© 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. 22-GEMMASCOPE-RES-131K
    7. 130965
    Prev
    Next
    INDEX
    Explanations

    higher than or lower than

    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_22/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
     continually
    -1.51
     lavora
    -1.47
     attraverso
    -1.45
     risulta
    -1.20
     farà
    -1.17
     potrivit
    -1.17
     faptul
    -1.16
     dovre
    -1.16
     veramente
    -1.16
     avrà
    -1.15
    POSITIVE LOGITS
     in
    2.28
     from
    1.57
     by
    1.52
     at
    1.45
     if
    1.23
     fruta
    1.20
    ditionally
    1.15
     (
    1.13
     є
    1.10
     PUBLICATIONS
    1.09
    Activations Density 0.080%

    No Known Activations