© 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. 238552
    Prev
    Next
    INDEX
    Explanations

    responsible for duties

    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
    ป
    0.52
    adult
    0.50
    apro
    0.50
    surprise
    0.48
    ित
    0.47
    reporter
    0.47
    arap
    0.46
    ر
    0.46
     قلت
    0.46
    perd
    0.46
    POSITIVE LOGITS
     Eduardo
    0.55
     Untersuchungen
    0.54
     démon
    0.52
     leisten
    0.50
     multicultural
    0.50
     värld
    0.50
     Execution
    0.49
     vlastní
    0.48
     Sonny
    0.48
     Führ
    0.48
    Activations Density 0.001%

    No Known Activations