© 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. 97029
    Prev
    Next
    INDEX
    Explanations

    distracted driving detection

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

    troubleshooting instructions and warnings

    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
    וחות
    0.47
     مشتری
    0.46
     obiettivi
    0.45
     underpin
    0.44
     habíamos
    0.44
    atschapp
    0.44
     apaixon
    0.43
    颢
    0.43
    ی
    0.43
     pensamiento
    0.43
    POSITIVE LOGITS
    segments
    0.44
    ansk
    0.42
    .,
    0.41
    塩素
    0.41
     aeration
    0.41
     belt
    0.40
    neat
    0.40
    angle
    0.40
    Skirt
    0.40
    kn
    0.39
    Activations Density 0.000%

    No Known Activations