© 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. 77179
    Prev
    Next
    INDEX
    Explanations

    bicycle components and maintenance

    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
     pedals
    -0.94
    ợt
    -0.77
     Billy
    -0.75
    geometry
    -0.75
     кол
    -0.73
     Stefano
    -0.72
     Ped
    -0.71
     rowIndex
    -0.70
    pedal
    -0.69
     pedal
    -0.68
    POSITIVE LOGITS
     troupes
    0.81
     levers
    0.81
     MTB
    0.79
     Branson
    0.78
     Ctr
    0.75
    amarca
    0.75
     WJ
    0.73
    ctv
    0.72
    вший
    0.72
     bosses
    0.72
    Activations Density 0.012%

    No Known Activations