© 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. 81166
    Prev
    Next
    INDEX
    Explanations

    year, available, or arrest following tokens

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

    your [noun]

    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
     Economics
    0.55
    酴
    0.48
     ख़ास
    0.47
     ERC
    0.46
     IT
    0.46
     economics
    0.46
     RBI
    0.46
     comments
    0.45
     গিয়ে
    0.45
     Hunt
    0.45
    POSITIVE LOGITS
     dormir
    0.48
    していない
    0.48
     beweg
    0.48
    ља
    0.47
    ろ
    0.47
    اد
    0.47
     vestir
    0.47
    ره
    0.47
    ﺣ
    0.46
     século
    0.45
    Activations Density 0.001%

    No Known Activations