© 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. 114550
    Prev
    Next
    INDEX
    Explanations

    vehicle safety assistance features

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

    autonomous driving safety

    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
     موب
    0.44
    刁
    0.41
     Règ
    0.40
     витами
    0.40
    槭
    0.40
     Phon
    0.39
     músicos
    0.39
    āb
    0.39
    叄
    0.39
    鉆
    0.39
    POSITIVE LOGITS
     lidar
    0.56
    Safety
    0.55
    ADAS
    0.51
     lane
    0.51
     safety
    0.50
     radars
    0.48
     radar
    0.47
     vigilance
    0.47
    Lane
    0.46
    Autonomous
    0.46
    Activations Density 0.051%

    No Known Activations