© 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. 14215
    Prev
    Next
    INDEX
    Explanations

    save or get

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

    Box Geometry

    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
    痱
    0.50
    تم
    0.46
     certaine
    0.43
    ował
    0.42
    ება
    0.42
    يش
    0.42
     শুকনো
    0.41
    ű
    0.41
    ewood
    0.40
    Der
    0.40
    POSITIVE LOGITS
     调用
    0.44
     通
    0.41
     dimes
    0.41
     typing
    0.41
     shader
    0.40
     佐
    0.40
     transcoding
    0.40
     notebook
    0.39
     monol
    0.39
     savez
    0.39
    Activations Density 0.000%

    No Known Activations