© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51110
    Prev
    Next
    INDEX
    Explanations

    type or scope or presentation

    np_acts-logits-general · gemini-2.5-flash-lite

    classification or type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     عنده
    0.49
    InputDialog
    0.46
    niejszych
    0.43
    KeyboardView
    0.40
     장면
    0.39
     حداقل
    0.38
    㕮
    0.38
    errorhandler
    0.38
    otry
    0.38
    э
    0.38
    POSITIVE LOGITS
     type
    0.83
     tipo
    0.76
    type
    0.73
    类型
    0.71
     TYPE
    0.71
    TYPE
    0.71
     whether
    0.70
    whether
    0.67
     types
    0.66
     getType
    0.66
    Activations Density 0.030%

    No Known Activations