© 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. 195310
    Prev
    Next
    INDEX
    Explanations

    dumpster, appreciate, region

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

    list items followed by descriptors

    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
     निर्धारण
    0.52
    ,?
    0.49
    rones
    0.48
    nesday
    0.47
     (),
    0.46
    ~(
    0.45
     特別
    0.45
     ().
    0.45
     विधेयक
    0.44
     なさい
    0.44
    POSITIVE LOGITS
    ራ
    0.51
    סה
    0.50
    ዳል
    0.49
    스키
    0.47
    앓
    0.46
     proiect
    0.46
    يكا
    0.45
    妧
    0.44
     cytology
    0.44
    ཟ
    0.43
    Activations Density 0.000%

    No Known Activations