© 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. 224314
    Prev
    Next
    INDEX
    Explanations

    traditional preparations, guest

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

    "is" followed by adjectives or specific descriptors

    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
    <unused89>
    0.48
     Strategies
    0.48
     ゲーム
    0.47
    䛛
    0.47
    gameState
    0.47
    ڈر
    0.47
     антен
    0.46
     ವಿಧಾನ
    0.46
     者
    0.45
    γρά
    0.45
    POSITIVE LOGITS
     آتش
    0.45
     ub
    0.44
    ubit
    0.44
     çıkar
    0.43
     verdadeiro
    0.43
     name
    0.43
     ur
    0.43
    因为
    0.42
     deng
    0.42
     imprimir
    0.42
    Activations Density 0.000%

    No Known Activations