© 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. 82518
    Prev
    Next
    INDEX
    Explanations

    variable assignment or structure

    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
    至
    0.43
    笼
    0.40
    retch
    0.39
    ουσ
    0.39
    的方法
    0.39
    ActionsCallback
    0.38
    dawn
    0.38
    deltaTime
    0.37
    防止
    0.37
    推出的
    0.37
    POSITIVE LOGITS
     PMI
    0.56
     En
    0.53
     G
    0.50
     L
    0.49
     passionately
    0.49
     quyết
    0.49
     MIN
    0.49
     BIR
    0.48
     Pre
    0.48
     Fin
    0.48
    Activations Density 0.003%

    No Known Activations