© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 83714
    Prev
    Next
    INDEX
    Explanations

    lane keeping and departure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ',$
    0.45
    헤
    0.41
    ***",
    0.40
    
    0.39
     헤
    0.38
    dataPath
    0.38
     sidewalks
    0.36
     vozila
    0.36
    
    0.35
    хе
    0.35
    POSITIVE LOGITS
     Keeping
    0.57
     keeping
    0.55
    keeping
    0.45
     Roche
    0.43
     Departure
    0.42
     maintaining
    0.42
    ROIT
    0.42
     Maintaining
    0.41
     Changing
    0.41
     keepers
    0.41
    Activations Density 0.000%

    No Known Activations