© 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. 155630
    Prev
    Next
    INDEX
    Explanations

    USA locations

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

    knots prevent

    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
     Color
    0.47
    Color
    0.46
    купно
    0.46
    Prim
    0.45
    Shr
    0.45
    ামার
    0.45
     Oxidation
    0.44
    畕
    0.44
     пенсион
    0.44
     anodic
    0.43
    POSITIVE LOGITS
     järjest
    0.57
    ್ಧ
    0.50
    REETYPE
    0.47
    ponsorship
    0.46
    hops
    0.46
    authors
    0.45
    آ
    0.45
    picklist
    0.45
     മേ
    0.44
    pielt
    0.44
    Activations Density 0.000%

    No Known Activations