© 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. 130904
    Prev
    Next
    INDEX
    Explanations

    estate planning and farming

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

    identification, division, suspect

    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
     흰
    0.53
     peralatan
    0.52
     Ovaj
    0.52
     уйна
    0.51
     Gitar
    0.51
     żół
    0.50
     лінії
    0.50
     ilość
    0.50
     издели
    0.49
     oxyd
    0.49
    POSITIVE LOGITS
    s
    0.58
    um
    0.55
    in
    0.52
    ir
    0.52
    ol
    0.51
     who
    0.51
    o
    0.51
    f
    0.51
    em
    0.50
    un
    0.50
    Activations Density 0.000%

    No Known Activations