© 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. 114968
    Prev
    Next
    INDEX
    Explanations

    profit organization

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

    . find a. find thefind afind thefind upfind modelscatch up. booking. num. best

    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
    ită
    0.56
     ();
    0.45
     identifik
    0.44
    离婚
    0.43
    囃
    0.42
    itado
    0.42
    hesu
    0.42
     тър
    0.42
     ویک
    0.42
    ψει
    0.42
    POSITIVE LOGITS
    /
    0.60
     Leah
    0.50
     SRC
    0.48
     PMA
    0.48
     Braun
    0.47
     Shaft
    0.46
    ./
    0.46
     Tulip
    0.46
     Sunlight
    0.45
     Jonas
    0.45
    Activations Density 0.000%

    No Known Activations