© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 75706
    Prev
    Next
    INDEX
    Explanations

    pedestrians and vehicles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cjach
    -0.82
     publishers
    -0.77
    rées
    -0.75
    orderItem
    -0.73
    traffic
    -0.71
    prefix
    -0.71
    ือง
    -0.71
    hemis
    -0.70
    polis
    -0.69
    instant
    -0.69
    POSITIVE LOGITS
     walking
    2.98
     pedestrians
    2.97
     pedestrian
    2.77
     walkers
    2.44
     walk
    2.36
    Walking
    2.31
    walking
    2.30
     bicy
    2.19
     WALK
    2.16
     walker
    2.13
    Activations Density 0.034%

    No Known Activations