© 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. 84178
    Prev
    Next
    INDEX
    Explanations

    success, failure, worth, steps, types

    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
    -
    -3.75
    "
    -2.73
    (
    -2.63
    ’
    -2.58
    ?
    -2.42
    럿
    -2.42
    ことも
    -2.31
    ↵↵
    -2.31
     здесь
    -2.27
     เพราะ
    -2.27
    POSITIVE LOGITS
    鹇
    3.00
    骜
    2.84
    骓
    2.75
    "])
    2.73
    "]);
    2.72
    นี้
    2.63
    〜。
    2.61
    鯓
    2.53
    呖
    2.50
    驁
    2.48
    Activations Density 0.002%

    No Known Activations