© 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. 40821
    Prev
    Next
    INDEX
    Explanations

    nx

    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
    ”;
    -2.91
    );
    -2.80
    a
    -2.66
    逦
    -2.64
    the
    -2.55
    arynx
    -2.53
    ’
    -2.52
    -2.47
     возможность
    -2.45
    ”.
    -2.44
    POSITIVE LOGITS
    矬
    2.86
    櫺
    2.55
    них
    2.44
     impoverished
    2.38
    ៚
    2.31
    蟥
    2.28
    开玩笑
    2.28
     bedrock
    2.25
    小孩子
    2.25
    άν
    2.22
    Activations Density 0.001%

    No Known Activations