© 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. 81706
    Prev
    Next
    INDEX
    Explanations

    off-road terrain

    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
     fiets
    -0.91
    Workbench
    -0.90
    culares
    -0.82
     vélo
    -0.82
    Motorcycle
    -0.81
    umbus
    -0.81
     Motorcycle
    -0.79
    opaque
    -0.79
     bicic
    -0.79
    ργα
    -0.79
    POSITIVE LOGITS
     terrain
    1.91
     off
    1.70
    terrain
    1.59
     rugged
    1.57
     rough
    1.57
     adventure
    1.38
     offroad
    1.35
    Terrain
    1.33
     Terrain
    1.27
     capabilities
    1.24
    Activations Density 0.025%

    No Known Activations