© 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. 50511
    Prev
    Next
    INDEX
    Explanations

    business, legal, and religious contexts

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

    variations and specific follow-ups

    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
     مست
    0.51
     refineries
    0.48
     guardians
    0.47
    <$
    0.46
     العالمين
    0.45
    ulated
    0.44
    銜
    0.44
    questions
    0.44
     dissipated
    0.44
     الب
    0.43
    POSITIVE LOGITS
     construit
    0.52
     Chord
    0.50
    리즈
    0.49
    গ
    0.49
     Alegre
    0.48
     artı
    0.48
     Dispatch
    0.48
     También
    0.48
     Dès
    0.48
     creativo
    0.47
    Activations Density 0.000%

    No Known Activations