© 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. 228178
    Prev
    Next
    INDEX
    Explanations

    power, movies, surgery, image

    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
     FODC
    0.64
    ूस
    0.59
     lesquelles
    0.56
    िकास
    0.52
    ﮔ
    0.50
     OCPP
    0.49
     sparsim
    0.49
     lesquels
    0.49
    ضافة
    0.48
    بلغ
    0.48
    POSITIVE LOGITS
    i
    0.64
    il
    0.57
    in
    0.57
    ope
    0.54
    o
    0.54
    ig
    0.53
    ij
    0.52
    ed
    0.52
    hak
    0.51
    en
    0.49
    Activations Density 0.000%

    No Known Activations