© 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. 43760
    Prev
    Next
    INDEX
    Explanations

    reason why or for

    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
    derdag
    -3.31
    雰
    -3.13
    哙
    -3.03
    廕
    -2.97
    ᐡ
    -2.92
    ︓
    -2.92
    🦤
    -2.89
    喾
    -2.88
     penilaian
    -2.84
     This
    -2.80
    POSITIVE LOGITS
    ↵↵
    4.03
    .
    3.78
    ar
    3.28
    at
    3.03
    n
    3.00
    v
    2.98
    in
    2.88
    ‘
    2.88
    <em>
    2.80
    7
    2.77
    Activations Density 0.013%

    No Known Activations