© 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-65K
    7. 46010
    Prev
    Next
    INDEX
    Explanations

    depending on formality

    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_65k_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
     查询
    0.52
     financed
    0.50
     +(
    0.50
     Syrup
    0.49
    ]+
    0.49
     ກ
    0.48
     lumped
    0.48
     ១
    0.48
     处理
    0.47
     플러스
    0.47
    POSITIVE LOGITS
    By
    0.53
    Role
    0.51
    Cour
    0.50
    ل
    0.49
    ल
    0.49
    Close
    0.48
    بال
    0.47
    Wra
    0.46
    Size
    0.46
    Email
    0.46
    Activations Density 0.007%

    No Known Activations