© 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. 44252
    Prev
    Next
    INDEX
    Explanations

    time since

    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
    -1.58
     dilutions
    -1.45
    䊏
    -1.45
    jgl
    -1.43
     erik
    -1.38
    ໌
    -1.37
    ​—
    -1.35
     чрезвы
    -1.35
     microphones
    -1.35
     is
    -1.35
    POSITIVE LOGITS
    н
    1.52
     '
    1.52
    '
    1.49
     we
    1.46
     либо
    1.38
     我们
    1.38
    []{"
    1.38
    к
    1.36
    ﺲ
    1.30
    чей
    1.28
    Activations Density 0.011%

    No Known Activations