© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117111
    Prev
    Next
    INDEX
    Explanations

    road numbers and main lines

    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
    xffffffff
    -0.79
     faibles
    -0.76
    IBarButtonItem
    -0.76
     récon
    -0.75
     déchir
    -0.74
    HMM
    -0.74
    ibição
    -0.73
    omitempty
    -0.72
     xu
    -0.72
    limp
    -0.72
    POSITIVE LOGITS
     road
    1.22
     jalan
    1.04
     roads
    0.97
    road
    0.93
     at
    0.93
    Road
    0.90
     strada
    0.87
    альное
    0.83
     Road
    0.83
     trunk
    0.82
    Activations Density 0.016%

    No Known Activations