© 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. 42337
    Prev
    Next
    INDEX
    Explanations

    applicable laws or taxes

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

    foreign words and fragments

    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
    古い
    0.58
    ETER
    0.54
    Archive
    0.53
    არ
    0.48
    Error
    0.48
    これが
    0.48
    ＿
    0.47
    ალ
    0.47
    オ
    0.47
    ეგ
    0.47
    POSITIVE LOGITS
    नीत
    0.46
     abortion
    0.46
     abe
    0.46
     neće
    0.46
     mumbled
    0.46
     treba
    0.46
     robi
    0.46
     disfraz
    0.45
     sabb
    0.45
     attached
    0.45
    Activations Density 0.000%

    No Known Activations