© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 149858
    Prev
    Next
    INDEX
    Explanations

    creative talent and performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bessel
    0.81
     RCC
    0.71
    IBM
    0.69
     දැ
    0.67
     guessed
    0.67
    嬷
    0.66
    ibacter
    0.66
     wrestle
    0.66
    MNIST
    0.66
    WWE
    0.66
    POSITIVE LOGITS
     Creative
    0.82
    顿
    0.81
     Direction
    0.81
     क्रिएट
    0.78
     creative
    0.75
     Rotation
    0.74
     Talent
    0.73
     Tung
    0.70
    Direction
    0.69
     Constituição
    0.69
    Activations Density 0.002%

    No Known Activations