© 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. 194823
    Prev
    Next
    INDEX
    Explanations

    studies prove

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

    OpenAI API Access

    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
    䋇
    0.52
     ребен
    0.50
     కనిప
    0.49
    ሒ
    0.49
    淍
    0.49
     నేను
    0.49
     दूसरा
    0.48
    妗
    0.48
    நீங்கள்
    0.48
    軹
    0.48
    POSITIVE LOGITS
    -
    0.66
    _
    0.56
    </b>
    0.54
    ga
    0.47
    ın
    0.46
    é
    0.46
    ato
    0.46
    frac
    0.46
    agu
    0.45
     incremental
    0.45
    Activations Density 0.001%

    No Known Activations