© 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. 40-GEMMASCOPE-2-RES-262K
    7. 136573
    Prev
    Next
    INDEX
    Explanations

    flat, flexible, usual, roof

    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_40_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
     withheld
    0.43
     Осо
    0.40
    avljen
    0.40
    وده
    0.39
     spie
    0.39
    itted
    0.39
    owed
    0.38
    Ọ
    0.38
    힣
    0.37
     unary
    0.37
    POSITIVE LOGITS
    秫
    0.52
     recetas
    0.45
    鳃
    0.43
    갑
    0.42
    这些人
    0.41
    طم
    0.41
    anesulf
    0.40
    መል
    0.39
    隐含规则
    0.39
    चक
    0.39
    Activations Density 0.000%

    No Known Activations