© 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. 54172
    Prev
    Next
    INDEX
    Explanations

    population was X

    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
    _",
    -1.08
    ೦
    -1.06
    Bool
    -1.06
     mieli
    -1.05
    ENAS
    -1.05
    since
    -1.03
    mère
    -1.02
    駸
    -1.02
    ๒
    -1.02
    Already
    -1.01
    POSITIVE LOGITS
     and
    1.34
    辯
    1.07
     numerosas
    0.96
     in
    0.93
    變得
    0.92
     asked
    0.90
    場所に
    0.88
    vska
    0.88
     out
    0.87
     moved
    0.87
    Activations Density 0.000%

    No Known Activations