© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146522
    Prev
    Next
    INDEX
    Explanations

    information on booking and contact

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

    logic gates

    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
     apna
    0.52
     baseHP
    0.52
    ůj
    0.49
     केक
    0.48
     মোহন
    0.47
    耖
    0.47
     prophes
    0.46
     apni
    0.46
     Caedwalla
    0.46
     عين
    0.46
    POSITIVE LOGITS
    are
    0.54
    at
    0.51
     <
    0.51
    un
    0.49
    à
    0.49
    ing
    0.49
    erve
    0.49
     multif
    0.49
    urally
    0.48
    L
    0.48
    Activations Density 0.000%

    No Known Activations