© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60118
    Prev
    Next
    INDEX
    Explanations

    calculated from

    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
     .......
    -1.88
     cette
    -1.87
     ........
    -1.85
    蹰
    -1.82
     !!!!
    -1.68
    楽しんで
    -1.66
    )$.
    -1.66
     dieser
    -1.63
     alcune
    -1.63
    seems
    -1.61
    POSITIVE LOGITS
     with
    2.42
     on
    2.25
     and
    2.23
     from
    2.05
     in
    1.91
    t
    1.87
     an
    1.86
     information
    1.84
     because
    1.84
     or
    1.82
    Activations Density 0.043%

    No Known Activations