© 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. 24570
    Prev
    Next
    INDEX
    Explanations

    ordinary, update, best, PDF, cured, spirit

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

    modal verbs and nouns

    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
     instantiate
    0.47
     उसने
    0.47
     reflectance
    0.44
     flare
    0.43
     পক্ষে
    0.42
     coaxial
    0.42
    蘖
    0.42
     এটি
    0.41
    Configure
    0.41
    Thing
    0.41
    POSITIVE LOGITS
     Giang
    0.46
    уна
    0.46
     現
    0.46
     المحلي
    0.45
    鈈
    0.45
     Herzeg
    0.45
     명
    0.42
     問
    0.42
    estim
    0.42
    和小
    0.42
    Activations Density 0.000%

    No Known Activations