© 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. 183979
    Prev
    Next
    INDEX
    Explanations

    first full, Austrian university

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

    Which I mean

    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
     amerikan
    0.47
    Getter
    0.46
    atin
    0.45
    ink
    0.45
     weer
    0.44
    밂
    0.44
     aank
    0.43
     sogenannte
    0.43
    برا
    0.43
     sogen
    0.43
    POSITIVE LOGITS
     lý
    0.47
    arello
    0.45
     :]
    0.43
     х
    0.42
     ನಿರ್
    0.42
     unaccount
    0.42
     special
    0.41
     специа
    0.41
    ずる
    0.41
    <0x8F>
    0.41
    Activations Density 0.000%

    No Known Activations