© 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. 86607
    Prev
    Next
    INDEX
    Explanations

    gothic elements

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

    command line phrases

    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
    y
    0.57
    yuan
    0.54
    SHA
    0.53
    ators
    0.48
    گان
    0.48
    pere
    0.48
    ATORS
    0.48
    ue
    0.47
    埤
    0.47
    z
    0.47
    POSITIVE LOGITS
    営業時間
    0.47
     ενώ
    0.46
     marin
    0.44
     codebase
    0.44
    رسٹ
    0.43
    मीडिया
    0.41
     আর্থিক
    0.40
     eğer
    0.40
     coupons
    0.39
    কেশন
    0.39
    Activations Density 0.000%

    No Known Activations