© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11208
    Prev
    Next
    INDEX
    Explanations

    code construction

    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
     remain
    -1.07
     an
    -1.01
     noteworthy
    -0.99
     determining
    -0.98
     Daniel
    -0.98
     providing
    -0.97
     one
    -0.93
     Robert
    -0.93
    let
    -0.92
    ,
    -0.91
    POSITIVE LOGITS
     zarówno
    1.21
     espect
    1.09
    kelijk
    1.09
     restes
    1.09
     proph
    1.08
     !!}
    1.06
    basically
    1.06
     både
    1.05
     commerci
    1.05
    both
    1.04
    Activations Density 0.049%

    No Known Activations