© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 134313
    Prev
    Next
    INDEX
    Explanations

    as described

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers, `One`, `False`, `league`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ันท
    0.44
    ertung
    0.43
    ন
    0.42
    唝
    0.42
    Lapangan
    0.41
    सिटी
    0.41
    饵
    0.41
    蹋
    0.41
    门口
    0.41
    Ripe
    0.41
    POSITIVE LOGITS
     exquisitely
    0.52
     extraordinarily
    0.50
     থাকত
    0.48
     permanently
    0.48
     pancreas
    0.47
     BRCA
    0.47
     represent
    0.46
     h
    0.46
     Germany
    0.45
     alignment
    0.45
    Activations Density 0.001%

    No Known Activations