© 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. 78756
    Prev
    Next
    INDEX
    Explanations

    extremely dangerous, severe legal

    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
    锑
    0.54
    𒅗
    0.52
     \%
    0.50
    ؛
    0.50
     attham
    0.50
    owlapi
    0.48
    owią
    0.47
    വൃത്തി
    0.47
    Deleting
    0.47
    ":"
    0.46
    POSITIVE LOGITS
    на
    0.50
     have
    0.44
     faint
    0.43
     облада
    0.41
     conic
    0.41
     incon
    0.40
     clears
    0.40
     осуществля
    0.39
     aren
    0.39
    গত
    0.39
    Activations Density 0.000%

    No Known Activations