© 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. 3986
    Prev
    Next
    INDEX
    Explanations

    file paths

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

    Python file paths

    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
     détermine
    0.36
     relatifs
    0.35
    丵
    0.35
    kében
    0.35
     doré
    0.35
    ㄺ
    0.34
     scheduler
    0.34
    scheduler
    0.34
    ➚
    0.34
     연락
    0.34
    POSITIVE LOGITS
     Neo
    0.40
    Neo
    0.37
     And
    0.33
    and
    0.33
    &
    0.33
    aci
    0.33
     Castro
    0.33
    ...\...\...\...\
    0.32
    0.32
     Hey
    0.31
    Activations Density 0.000%

    No Known Activations