© 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. 861
    Prev
    Next
    INDEX
    Explanations

    la la-la, лалалупси, XAAR

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

    acronyms and abbreviations

    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
    އ
    0.72
    ک
    0.67
    ষধ
    0.62
    ನಿ
    0.61
    থাৎ
    0.61
    T
    0.61
    સ
    0.61
    د
    0.59
    ਕ
    0.59
    মের
    0.58
    POSITIVE LOGITS
    '
    0.95
    e
    0.79
    er
    0.76
    et
    0.72
     are
    0.71
     was
    0.71
    ार
    0.71
    p
    0.69
    en
    0.69
    ani
    0.65
    Activations Density 1.324%

    No Known Activations