© 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. 178040
    Prev
    Next
    INDEX
    Explanations

    reasonable costs and debris

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

    east, west, anything

    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
     Zwischen
    0.47
     कथित
    0.45
     เปลี่ยน
    0.45
     salida
    0.44
    after
    0.44
     Javed
    0.44
     Umsatz
    0.43
    л
    0.43
     трёх
    0.42
    櫳
    0.42
    POSITIVE LOGITS
    大于
    0.48
     physiology
    0.47
    ोटो
    0.46
     abstinence
    0.45
    HX
    0.44
    owników
    0.43
     organs
    0.43
    皮
    0.43
    ㅏ
    0.43
     axioms
    0.43
    Activations Density 0.002%

    No Known Activations