© 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. 70848
    Prev
    Next
    INDEX
    Explanations

    consists of, contain, or disk drive

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

    Identifying widget/app constants

    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
     intégral
    0.50
     өз
    0.47
     cityName
    0.45
    숍
    0.45
    돛
    0.45
    ју
    0.44
    確保
    0.44
    ść
    0.44
    мию
    0.44
     конкурс
    0.44
    POSITIVE LOGITS
    1
    0.50
     When
    0.48
     Eventually
    0.47
    ago
    0.45
    where
    0.45
     ADHD
    0.43
     &
    0.43
    debug
    0.42
     Males
    0.42
    example
    0.41
    Activations Density 0.001%

    No Known Activations