© 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. 67939
    Prev
    Next
    INDEX
    Explanations

    megapixels, SSE, Lovato, Chandra

    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
    🦣
    -2.80
    ၞ
    -2.78
     catedral
    -2.75
     a
    -2.66
     nerede
    -2.64
     „
    -2.58
     Schwerpunkt
    -2.38
     yanında
    -2.36
    哙
    -2.36
    其妙
    -2.34
    POSITIVE LOGITS
    s
    3.17
    _{
    3.06
    es
    2.72
    ल
    2.63
    on
    2.53
    ی
    2.50
    ჻
    2.47
    2
    2.42
    <bos>
    2.41
    ات
    2.31
    Activations Density 0.008%

    No Known Activations