© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15059
    Prev
    Next
    INDEX
    Explanations

    section labels after dividers

    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
    ).
    -2.28
    ),
    -2.14
    in
    -2.06
    ".
    -1.76
    ↵
    -1.76
    霎
    -1.72
     but
    -1.70
     comprising
    -1.67
    tedì
    -1.65
    ",
    -1.62
    POSITIVE LOGITS
    ᐕ
    2.22
    峩
    2.20
    錾
    2.11
    这
    2.05
    噲
    1.99
    桫
    1.98
    ޏ
    1.98
    ',
    1.92
    1.91
     Reſ
    1.91
    Activations Density 0.004%
    No Known Activations