© 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. 60803
    Prev
    Next
    INDEX
    Explanations

    tranquil south, wild, urge, machine will, exactly

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

    preferred method choice

    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
    レスレット
    0.52
    ２
    0.52
    パナソニック
    0.50
     étudiant
    0.49
    ปร
    0.47
     kurie
    0.47
    スター
    0.47
     kuri
    0.47
     europeo
    0.46
     verfügen
    0.46
    POSITIVE LOGITS
     erupted
    0.50
     watery
    0.45
     र
    0.45
     osc
    0.44
    osc
    0.44
     homoc
    0.43
     sealed
    0.43
     හැ
    0.43
     aqueous
    0.42
     diluted
    0.42
    Activations Density 0.000%

    No Known Activations