© 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. 106836
    Prev
    Next
    INDEX
    Explanations

    motorcycle

    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
     deleteAll
    -0.77
    INSTALLATION
    -0.71
    诈
    -0.71
     Another
    -0.69
     camión
    -0.69
    主催
    -0.66
     ANOTHER
    -0.66
     sort
    -0.66
     Bilateral
    -0.66
     thin
    -0.66
    POSITIVE LOGITS
    taxis
    0.94
    taxi
    0.94
    χαν
    0.84
    sikal
    0.81
    риста
    0.81
     diaries
    0.79
    cts
    0.78
    cross
    0.76
    логические
    0.75
    вери
    0.74
    Activations Density 0.031%

    No Known Activations