© 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. 39321
    Prev
    Next
    INDEX
    Explanations

    beginning of code or comment

    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
     programmet
    -1.56
     vijf
    -1.54
    seven
    -1.47
     móc
    -1.44
     necesit
    -1.40
     villes
    -1.40
     Aceite
    -1.35
    several
    -1.34
    showing
    -1.34
     filmen
    -1.34
    POSITIVE LOGITS
     from
    1.77
     will
    1.65
     on
    1.63
     in
    1.63
     use
    1.47
     after
    1.45
     -
    1.41
     mín
    1.39
     data
    1.37
     like
    1.36
    Activations Density 0.046%

    No Known Activations