© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 24125
    Prev
    Next
    INDEX
    Explanations

    speaking, teaching, or presenting

    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
    闖
    0.47
    闯
    0.44
     светло
    0.41
    努力
    0.39
     guerras
    0.39
     Theorems
    0.37
    Businessman
    0.37
    த்தக்க
    0.37
    睒
    0.37
     жа
    0.36
    POSITIVE LOGITS
     officiating
    0.81
     lecturing
    0.81
     conducting
    0.79
     offici
    0.78
    主持
    0.77
     teaching
    0.75
     Conducting
    0.75
     teach
    0.70
     preside
    0.68
     hosting
    0.67
    Activations Density 0.005%

    No Known Activations