© 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. 102576
    Prev
    Next
    INDEX
    Explanations

    various languages

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

    sensitivity and

    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
     tortillas
    0.54
     músculos
    0.52
    ajte
    0.50
    rites
    0.50
     pantalones
    0.48
    膀
    0.48
     sandals
    0.47
     fidget
    0.47
     talon
    0.47
    閑
    0.46
    POSITIVE LOGITS
    কুম
    0.49
     సంవత్సర
    0.46
     Cumhuriyet
    0.46
     Schaff
    0.46
    Jahr
    0.44
     TRANSPORTURI
    0.44
    年份
    0.44
     ==
    0.43
    맡
    0.43
     напи
    0.42
    Activations Density 0.008%

    No Known Activations