© 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. 182526
    Prev
    Next
    INDEX
    Explanations

    self-control, fabrics, restaurant

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

    various biological and conceptual entities

    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
     এরূপ
    0.48
    𒉣
    0.47
     элементы
    0.46
     юк
    0.45
    와의
    0.45
     ശി
    0.45
    EVA
    0.45
    CNC
    0.44
    Simplified
    0.44
    嗳
    0.44
    POSITIVE LOGITS
    ěstí
    0.40
    0
    0.40
    utils
    0.40
    hta
    0.39
    স্বাধীন
    0.39
     homebuyers
    0.39
    uber
    0.38
    arant
    0.38
     živ
    0.38
     জুলাই
    0.38
    Activations Density 0.001%

    No Known Activations