© 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. 177672
    Prev
    Next
    INDEX
    Explanations

    in the / on / email / commercial

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

    time ranges or durations

    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
     Digestive
    0.55
     సాహిత్య
    0.52
     méthode
    0.52
     проводить
    0.52
    SrvGroup
    0.50
     நவ
    0.50
     습
    0.50
     Tvam
    0.49
     വര്‍ഷ
    0.49
    雬
    0.49
    POSITIVE LOGITS
    ان
    0.55
    ل
    0.49
    5
    0.48
     strength
    0.48
     a
    0.46
    性
    0.46
    4
    0.46
     customers
    0.45
    ть
    0.45
    petition
    0.45
    Activations Density 0.001%

    No Known Activations