© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109027
    Prev
    Next
    INDEX
    Explanations

    walking and meeting

    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
     summer
    -0.98
    antía
    -0.96
     churrasco
    -0.95
    summer
    -0.94
    Highway
    -0.93
     Acapulco
    -0.93
     vilja
    -0.93
     Ibiza
    -0.92
     luxo
    -0.92
     laboratorium
    -0.91
    POSITIVE LOGITS
     street
    1.41
     walking
    1.33
    Walking
    1.24
     Walking
    1.10
    walking
    1.07
     walked
    1.06
     subway
    1.04
     sidewalk
    1.04
     alley
    1.01
     tourist
    1.00
    Activations Density 0.027%

    No Known Activations