© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 128859
    Prev
    Next
    INDEX
    Explanations

    idea of how to jail shit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sek
    0.49
    ск
    0.48
    લ્સ
    0.48
    количество
    0.45
     districts
    0.45
    ̓
    0.44
     wiss
    0.44
    th
    0.43
     thrust
    0.43
     Panel
    0.43
    POSITIVE LOGITS
    荩
    0.48
    来到了
    0.47
    ရား
    0.46
    دو
    0.46
    /');
    0.44
    ག་
    0.44
    楽器
    0.43
    幼儿
    0.42
     গার্মেন্টস
    0.42
    恽
    0.42
    Activations Density 0.007%

    No Known Activations