© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 147772
    Prev
    Next
    INDEX
    Explanations

    Berg and Stand variations

    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
     Chameleon
    0.78
    eonium
    0.78
    <unused1639>
    0.73
    Sey
    0.72
    latego
    0.71
    ameleon
    0.70
    impero
    0.67
    %"},
    0.67
    кульп
    0.67
    <unused2094>
    0.65
    POSITIVE LOGITS
    生产
    0.81
    いただき
    0.70
    动态
    0.69
    傗
    0.69
    ensk
    0.68
    生產
    0.68
     Intake
    0.67
    ქვს
    0.67
    䀖
    0.67
    outputs
    0.66
    Activations Density 0.004%

    No Known Activations