© 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. 77029
    Prev
    Next
    INDEX
    Explanations

    racing, rally, and drivers

    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
    modore
    -0.77
    estanding
    -0.76
     СП
    -0.76
     road
    -0.75
    road
    -0.74
     Road
    -0.74
     roadmap
    -0.73
    ntp
    -0.71
    Discus
    -0.69
    sixth
    -0.69
    POSITIVE LOGITS
    RX
    0.98
    Monster
    0.95
     Monster
    0.95
     RX
    0.86
    monster
    0.85
     Ester
    0.81
     JsonConvert
    0.81
     rally
    0.79
     Nitro
    0.79
     Erz
    0.79
    Activations Density 0.014%

    No Known Activations