© 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. 236610
    Prev
    Next
    INDEX
    Explanations

    Ken Pat

    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
     hosszú
    0.59
     behandeling
    0.55
     weniger
    0.55
     codzien
    0.52
     ப
    0.52
     នៅ
    0.50
     pokry
    0.50
     preuve
    0.50
     animaux
    0.50
     jugador
    0.49
    POSITIVE LOGITS
    I
    0.59
    [
    0.57
    "
    0.54
    ”
    0.50
    里
    0.49
    आई
    0.48
    u
    0.47
    त
    0.46
    And
    0.46
    यो
    0.46
    Activations Density 0.000%

    No Known Activations