© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6892
    Prev
    Next
    INDEX
    Explanations

    deliberately manipulative

    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
    ர்ந்த
    0.50
     вашей
    0.50
    enste
    0.48
     народ
    0.48
     wd
    0.48
     నమో
    0.47
     농
    0.47
     వంటి
    0.46
    骑士
    0.46
    <unused635>
    0.46
    POSITIVE LOGITS
    These
    0.59
     these
    0.57
    টারে
    0.47
    these
    0.44
    這些
    0.44
     AIDS
    0.43
     These
    0.43
     protease
    0.43
     rac
    0.43
    ये
    0.42
    Activations Density 0.001%

    No Known Activations