© 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. 128283
    Prev
    Next
    INDEX
    Explanations

    code comments and foreign characters

    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
     even
    -1.30
    gså
    -1.28
     diesem
    -1.24
    Ҭ
    -1.19
     Polski
    -1.18
     "\
    -1.13
     Franse
    -1.13
     навіть
    -1.13
     ₹
    -1.11
     erroneous
    -1.11
    POSITIVE LOGITS
     that
    1.18
     
    1.02
    thien
    1.02
    コメ
    1.01
     nieve
    1.00
    イエ
    0.99
    “
    0.98
     funções
    0.97
    イケメン
    0.97
     أو
    0.96
    Activations Density 0.002%

    No Known Activations