© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34720
    Prev
    Next
    INDEX
    Explanations

    sentence structure markers

    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
    rások
    -1.15
     logiciels
    -1.09
     châssis
    -1.05
     disponível
    -1.04
    курен
    -1.03
    __________
    -1.03
    殃
    -1.03
     RECORDS
    -1.02
     POSSIBLE
    -1.02
     CAKE
    -1.02
    POSITIVE LOGITS
     and
    1.36
    Kilder
    1.23
     שהוא
    1.05
    There
    1.05
     used
    1.04
    bánh
    1.04
    Masukkan
    1.02
    日発売
    1.01
    Dimens
    1.01
    One
    1.01
    Activations Density 0.000%

    No Known Activations