© 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. 134972
    Prev
    Next
    INDEX
    Explanations

    books and poetry

    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
    熒
    0.54
     Gobern
    0.50
     Fourteen
    0.47
     Congressman
    0.46
     flattering
    0.45
     হিন
    0.45
    珈
    0.44
    َة
    0.44
     Sporting
    0.43
    焙
    0.43
    POSITIVE LOGITS
    aları
    0.50
    üm
    0.50
    related
    0.45
    ivities
    0.44
    isele
    0.44
    rsp
    0.44
    lly
    0.44
    ombr
    0.43
    nesses
    0.43
    V
    0.43
    Activations Density 0.000%

    No Known Activations