© 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. 65029
    Prev
    Next
    INDEX
    Explanations

    Branch point

    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
    方には
    -1.35
     balón
    -1.32
     schlaf
    -1.31
    ᯾
    -1.27
    人には
    -1.25
     lança
    -1.24
     vistos
    -1.23
    hijab
    -1.20
     polegadas
    -1.18
    大叔
    -1.18
    POSITIVE LOGITS
    rt
    1.35
    M
    1.31
     anguish
    1.29
    c
    1.29
    G
    1.28
     प्रत्य
    1.27
     it
    1.27
    rc
    1.25
    f
    1.24
     garlands
    1.23
    Activations Density 0.003%

    No Known Activations