© 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. 105977
    Prev
    Next
    INDEX
    Explanations

    numpy as

    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
    ،
    0.76
    iophorus
    0.56
    。(
    0.55
    amise
    0.53
    、
    0.53
    utilisation
    0.53
    á
    0.53
    acara
    0.52
     स्लाइड्स
    0.52
    ahanam
    0.52
    POSITIVE LOGITS
    </h2>
    0.53
    最终
    0.53
    \
    0.51
    普遍
    0.48
    后续
    0.48
    ραν
    0.48
     ვი
    0.48
     polynomial
    0.48
     etat
    0.48
    a
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.