© 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. 128782
    Prev
    Next
    INDEX
    Explanations

    transportation, impact, and style

    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
     ອ
    0.47
     Destroyer
    0.47
     steals
    0.46
     restricciones
    0.44
     allClasses
    0.43
     जेईई
    0.43
     USS
    0.42
     mágico
    0.42
    न्या
    0.41
     tho
    0.41
    POSITIVE LOGITS
    ，
    0.50
    стар
    0.48
    不
    0.48
    ных
    0.47
    ли
    0.46
    вых
    0.46
     tenderness
    0.44
    不明
    0.44
    由
    0.44
    графі
    0.43
    Activations Density 0.007%

    No Known Activations