© 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. 173033
    Prev
    Next
    INDEX
    Explanations

    drivers

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

    root or traditionally

    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
    クリスマス
    0.50
    ज
    0.46
    4
    0.46
    ଈ
    0.46
    Christmas
    0.46
    Fare
    0.46
    なった
    0.45
    ENDS
    0.44
    NR
    0.43
     冬
    0.42
    POSITIVE LOGITS
    टल
    0.46
    achio
    0.43
     sagittal
    0.42
     一个
    0.42
    tLogRow
    0.42
     hypothalamic
    0.41
     கரைய
    0.41
    ρίας
    0.41
    otropin
    0.40
    AllRef
    0.40
    Activations Density 0.002%

    No Known Activations