© 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. 22-GEMMASCOPE-RES-131K
    7. 15488
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and quotes

    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_22/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
    S
    -2.56
    \
    -2.30
    และ
    -2.23
    (
    -2.20
     This
    -2.19
     zweite
    -2.14
    そして
    -2.13
    M
    -2.09
    N
    -2.05
    B
    -2.03
    POSITIVE LOGITS
     ‚
    2.34
    ,,,,
    2.23
    луйста
    2.22
    鋱
    2.17
    奩
    2.17
     expresses
    2.08
    სქ
    2.08
    凩
    2.06
    眎
    2.00
    噥
    2.00
    Activations Density 0.020%

    No Known Activations