© 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. 184620
    Prev
    Next
    INDEX
    Explanations

    foreign language identifiers

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

    bypassing restraints and filters

    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
     wie
    0.52
    zí
    0.48
    ý
    0.48
     roof
    0.47
    ké
    0.45
     Assuming
    0.44
    ↵↵
    0.44
    arium
    0.44
    mě
    0.44
    )
    0.43
    POSITIVE LOGITS
    Caroline
    0.53
    ссию
    0.52
    가격
    0.51
    Voy
    0.49
    新たに
    0.49
    تل
    0.48
    ้อม
    0.48
    আত্ম
    0.47
    新た
    0.47
    现金
    0.46
    Activations Density 0.000%

    No Known Activations