© 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. 38934
    Prev
    Next
    INDEX
    Explanations

    addressed titles or names

    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
     Vaters
    -1.11
     it
    -1.02
     pisze
    -0.93
     remark
    -0.91
    banyak
    -0.90
    added
    -0.87
    吃了
    -0.86
     addition
    -0.86
     but
    -0.85
     group
    -0.82
    POSITIVE LOGITS
     prêtre
    1.07
    umab
    1.06
    良いです
    0.99
     beck
    0.93
     nomenclature
    0.93
    ání
    0.91
     ダイヤ
    0.91
    ſure
    0.91
    minated
    0.91
     hetzelfde
    0.90
    Activations Density 0.005%

    No Known Activations