© 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. 211055
    Prev
    Next
    INDEX
    Explanations

    exchange period

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

    activities related to specific skills or processes

    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
     अपेक्षित
    0.48
     Benim
    0.48
     Toni
    0.48
     दोघा
    0.47
     Kathryn
    0.45
     उधर
    0.45
     Enemy
    0.44
    ∼
    0.44
     Drink
    0.44
     Stomach
    0.44
    POSITIVE LOGITS
    to
    0.52
     şekilde
    0.49
     way
    0.48
     wafer
    0.47
     wa
    0.46
     powertrain
    0.45
    方式
    0.44
    形式
    0.44
     yapmış
    0.44
     waren
    0.43
    Activations Density 0.001%

    No Known Activations