© 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. 188261
    Prev
    Next
    INDEX
    Explanations

    p. ISBN, ISSN

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

    Behavioral economics, manga art, startup patterns

    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
    кг
    0.47
    គ
    0.46
    БУ
    0.46
    сез
    0.45
    Ви
    0.44
    кир
    0.44
    布
    0.44
    ар
    0.44
    П
    0.44
    administ
    0.44
    POSITIVE LOGITS
     ทั้ง
    0.58
     เสียง
    0.51
     Alberts
    0.49
     Mikh
    0.47
     Connell
    0.46
     haszn
    0.46
    เสียง
    0.46
     പ്രസി
    0.45
     শব্দের
    0.45
     deployed
    0.44
    Activations Density 0.000%

    No Known Activations