© 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. 141978
    Prev
    Next
    INDEX
    Explanations

    fulfillment, shipping, preparation

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

    psychological or suffix combinations

    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
    ADES
    0.48
     പക്ഷ
    0.46
    ཟ
    0.46
    าม
    0.45
    荖
    0.45
    ガイ
    0.45
    тись
    0.44
    ppsala
    0.44
    든
    0.43
     intensities
    0.43
    POSITIVE LOGITS
    inx
    0.47
    sort
    0.45
     agrade
    0.45
    removeFrom
    0.44
     beanie
    0.44
     immortal
    0.43
     egip
    0.43
    remember
    0.43
    print
    0.43
     incó
    0.43
    Activations Density 0.001%

    No Known Activations