© 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. 95122
    Prev
    Next
    INDEX
    Explanations

    insurance phone enter film book

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

    saving data or state

    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
     (
    0.54
     peric
    0.51
    ;
    0.51
     sonor
    0.50
    ائز
    0.49
     arid
    0.48
    ва
    0.48
    ری
    0.48
     incor
    0.47
     identity
    0.46
    POSITIVE LOGITS
     វា
    0.51
     YEAR
    0.50
    iking
    0.50
    u
    0.49
    क्रेट
    0.48
     नाराजगी
    0.47
     গণতন্ত্র
    0.47
    adion
    0.47
     평가
    0.46
     නමුත්
    0.46
    Activations Density 0.000%

    No Known Activations