© 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. 220279
    Prev
    Next
    INDEX
    Explanations

    japanese and punjabi words

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

    instruction and rules

    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
     anderes
    0.45
     ث
    0.43
     எல்லை
    0.43
     García
    0.43
    اری
    0.43
    Generic
    0.42
    omez
    0.42
     leren
    0.42
    óf
    0.42
     Guard
    0.41
    POSITIVE LOGITS
    めでとう
    0.48
    cccnc
    0.48
    来店
    0.48
    みると
    0.47
    VSLU
    0.47
    とにかく
    0.46
    す
    0.46
    醤
    0.45
     ਤੁਹਾ
    0.45
    すと
    0.44
    Activations Density 0.001%

    No Known Activations