© 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. 251370
    Prev
    Next
    INDEX
    Explanations

    made it, install it

    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
     Änderung
    0.52
     Approximation
    0.49
    ឡិច
    0.47
     Specification
    0.47
     алге
    0.47
    扦
    0.46
    ঙ্ক
    0.46
     లా
    0.46
    밂
    0.46
    嘊
    0.46
    POSITIVE LOGITS
    as
    0.50
     বেরিয়ে
    0.49
     entrepreneurial
    0.46
    to
    0.44
    weekday
    0.43
    な
    0.43
    につき
    0.42
     platter
    0.42
    bandwidth
    0.42
    index
    0.42
    Activations Density 0.000%

    No Known Activations