© 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. 94926
    Prev
    Next
    INDEX
    Explanations

    specific quantities or measurements

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

    processes, browser, bodies, old, means

    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
    n
    0.54
     Charleston
    0.48
     Einst
    0.47
     overgrown
    0.46
     iesp
    0.46
     хоте
    0.46
     manipular
    0.45
     trent
    0.44
     impediments
    0.44
     سعید
    0.44
    POSITIVE LOGITS
    電流
    0.50
     निभाने
    0.48
    形態
    0.47
    োগান
    0.45
    Nina
    0.44
    癥
    0.44
    醣
    0.43
    高性能
    0.43
    鵰
    0.43
    動力
    0.43
    Activations Density 0.000%

    No Known Activations