© 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. 81713
    Prev
    Next
    INDEX
    Explanations

    Deadpool & Wolverine

    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
    ूर्त
    0.52
    Compet
    0.52
    compet
    0.50
    ič
    0.45
    стар
    0.45
    ž
    0.45
    डॉ
    0.44
    média
    0.43
    François
    0.43
    Expl
    0.41
    POSITIVE LOGITS
     Kho
    0.46
     Moy
    0.45
     Baal
    0.45
     stationed
    0.44
     Chayin
    0.44
     Ja
    0.44
     Tr
    0.43
    '`--'`--
    0.43
     Leach
    0.42
     AAU
    0.42
    Activations Density 0.011%

    No Known Activations