© 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. 184840
    Prev
    Next
    INDEX
    Explanations

    purpose of sharing

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

    Nuwa, XMLHttpRequest, Sedan

    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
    蚋
    0.55
    வுக்கு
    0.49
     neutroph
    0.49
     resorption
    0.49
    遶
    0.48
    什麼
    0.48
     BRO
    0.47
     macroph
    0.47
    亞
    0.47
    ્સ
    0.47
    POSITIVE LOGITS
    lay
    0.61
    ploy
    0.55
    itan
    0.54
    lds
    0.54
    ower
    0.54
    oline
    0.53
    mad
    0.52
    utile
    0.52
    live
    0.52
    ivers
    0.51
    Activations Density 0.001%

    No Known Activations