© 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. 58988
    Prev
    Next
    INDEX
    Explanations

    driving and highway descriptions

    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
     Walk
    -0.98
     walks
    -0.94
     Flugzeug
    -0.91
     Walking
    -0.91
    Walk
    -0.90
    walk
    -0.84
     caminar
    -0.84
     WALK
    -0.83
     walk
    -0.82
     bãi
    -0.82
    POSITIVE LOGITS
     road
    1.37
    driving
    1.30
     scenic
    1.27
    Driving
    1.27
     driving
    1.20
     winding
    1.11
     Driving
    1.11
     drive
    1.10
    ขับ
    1.08
     curvy
    1.05
    Activations Density 0.028%

    No Known Activations