© 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. 130588
    Prev
    Next
    INDEX
    Explanations

    C program entry point

    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
    quisa
    0.47
     түз
    0.41
    ^{\#}\
    0.40
    Ctx
    0.39
    調
    0.39
     dô
    0.39
    ῷ
    0.39
    ای
    0.39
    Marc
    0.38
    писа
    0.38
    POSITIVE LOGITS
     Characters
    0.41
    characters
    0.39
     Character
    0.38
    sitting
    0.37
    character
    0.37
     gegenüber
    0.37
     Nigerians
    0.36
     CONDITIONS
    0.35
     carattere
    0.35
    ాలా
    0.35
    Activations Density 0.001%

    No Known Activations