© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2692
    Prev
    Next
    INDEX
    Explanations

    girl who fights

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     deportes
    1.78
     makeSound
    1.77
     Bedürfnisse
    1.77
    fordern
    1.74
     GTA
    1.73
    HttpServlet
    1.73
    3
    1.70
    لاك
    1.69
    7
    1.67
    <end_of_image>
    1.67
    POSITIVE LOGITS
     bung
    0.92
     beam
    0.86
     diffraction
    0.86
    dra
    0.84
     subsidy
    0.83
     nets
    0.82
     ups
    0.79
     tide
    0.79
     Kee
    0.78
    وبه
    0.77
    Activations Density 0.061%

    No Known Activations