© 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. 163593
    Prev
    Next
    INDEX
    Explanations

    book chapters and verses

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

    pattern recognition of common phrases

    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
     неба
    0.52
    omanian
    0.50
    筧
    0.48
    วิธีการ
    0.46
    亽
    0.46
     мину
    0.45
    वाह
    0.45
    ricane
    0.45
     UPPER
    0.45
    窿
    0.45
    POSITIVE LOGITS
     حين
    0.46
    ગે
    0.45
    exists
    0.44
     Routledge
    0.43
    읍
    0.42
     ٢
    0.42
    itura
    0.42
    eg
    0.42
    IllegalArgument
    0.42
     exhort
    0.41
    Activations Density 0.002%

    No Known Activations