© 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. 164967
    Prev
    Next
    INDEX
    Explanations

    payment and products

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

    complicated question RIS brushing allows

    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
    newspaper
    0.50
    лянчук
    0.49
     عيد
    0.48
    瀾
    0.47
    errorhandler
    0.47
     كانت
    0.46
     ಅಭಿ
    0.46
     були
    0.46
    astere
    0.46
    監
    0.46
    POSITIVE LOGITS
    I
    0.45
    ६
    0.44
     cements
    0.43
    al
    0.42
    ígeno
    0.42
    änen
    0.42
     bases
    0.42
     fuels
    0.41
    óis
    0.41
    éns
    0.41
    Activations Density 0.000%

    No Known Activations