© 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. 54750
    Prev
    Next
    INDEX
    Explanations

    import and export data

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

    imported into or as

    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
    ين
    0.87
    その
    0.86
    ی
    0.86
     فی
    0.82
    е
    0.80
    あり
    0.76
    _
    0.76
    投げ
    0.73
    は
    0.73
    ある
    0.71
    POSITIVE LOGITS
    u
    0.90
    t
    0.71
     Importing
    0.69
     t
    0.67
     import
    0.67
    import
    0.66
    ar
    0.65
    tól
    0.64
    eur
    0.63
     h
    0.62
    Activations Density 0.014%

    No Known Activations