© 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. 8813
    Prev
    Next
    INDEX
    Explanations

    the only thing

    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
    }$.
    -1.75
    美国
    -1.73
    )$.
    -1.73
    ”:
    -1.65
    ًا
    -1.65
    ágenes
    -1.65
    ԋ
    -1.63
    voegen
    -1.59
    ”;
    -1.55
    でも
    -1.53
    POSITIVE LOGITS
     we
    2.22
    '
    1.89
     that
    1.75
     могут
    1.63
     our
    1.61
    begin
    1.60
    帮你
    1.55
     terv
    1.55
     he
    1.53
     voelt
    1.53
    Activations Density 0.004%

    No Known Activations