© 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. 104747
    Prev
    Next
    INDEX
    Explanations

    variety

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

    multimeter, oscilloscope, simulator, analyzer

    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
     élevées
    0.50
    ịnh
    0.46
     همین
    0.44
    ñón
    0.43
    弁
    0.42
    зі
    0.42
    소년
    0.42
     internationales
    0.42
     magn
    0.42
    isés
    0.42
    POSITIVE LOGITS
    ;
    0.51
     विद्रोह
    0.50
    riots
    0.46
     Kashmiri
    0.46
    veyard
    0.46
     मुस्लिम
    0.45
    tissue
    0.44
    म
    0.44
    creep
    0.44
    ;//
    0.43
    Activations Density 0.001%

    No Known Activations