© 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. 9418
    Prev
    Next
    INDEX
    Explanations

    locations and organizations

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

    crisis help and resources

    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
    施術
    0.38
    অপর
    0.37
     wody
    0.36
    ielder
    0.35
     otra
    0.35
     drin
    0.35
     注
    0.35
     otro
    0.34
     호출
    0.34
     fname
    0.34
    POSITIVE LOGITS
     Harvard
    0.52
    澳门
    0.46
     International
    0.45
     University
    0.44
     Toronto
    0.44
     Canadian
    0.44
     National
    0.43
    National
    0.43
     U
    0.43
     Institute
    0.43
    Activations Density 0.134%

    No Known Activations