© 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. 60102
    Prev
    Next
    INDEX
    Explanations

    types of users

    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
     not
    -1.76
    ).
    -1.69
     from
    -1.66
     was
    -1.52
     which
    -1.51
    ↵
    -1.49
     they
    -1.48
     just
    -1.45
    ";
    -1.41
     recently
    -1.39
    POSITIVE LOGITS
    淠
    1.71
    tified
    1.63
    橚
    1.63
    𓍊
    1.57
    Ꮚ
    1.51
    presented
    1.48
    뿡
    1.48
     примеру
    1.48
    うわ
    1.47
    joyed
    1.45
    Activations Density 0.094%

    No Known Activations