© 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. 121209
    Prev
    Next
    INDEX
    Explanations

    locations and activities

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

    comparing prices or qualities

    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
    
    0.52
    undo
    0.47
    wania
    0.47
     الرا
    0.46
     appellees
    0.45
     importantes
    0.45
     ź
    0.43
     Ο
    0.43
    可在
    0.43
    ανο
    0.43
    POSITIVE LOGITS
     budget
    0.54
     pul
    0.48
    딩
    0.48
     letter
    0.46
     veg
    0.46
    潑
    0.44
     spir
    0.44
     pharmacy
    0.44
     supplement
    0.43
     slog
    0.42
    Activations Density 0.000%

    No Known Activations