© 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. 138374
    Prev
    Next
    INDEX
    Explanations

    worldwidemothermanadvanced computing

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

    command, character, singing

    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
    ueel
    0.59
    ag
    0.51
    طلح
    0.47
    лия
    0.46
    ใน
    0.46
    흡
    0.46
    的分
    0.45
    از
    0.45
    前
    0.45
    يك
    0.44
    POSITIVE LOGITS
     comedies
    0.56
     petitioners
    0.55
     andolan
    0.54
     implications
    0.50
     problem
    0.48
     ಇದರಿಂದ
    0.48
     spontaneity
    0.46
    Chips
    0.46
     esempio
    0.45
     comedy
    0.45
    Activations Density 0.000%

    No Known Activations