© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 146505
    Prev
    Next
    INDEX
    Explanations

    generative adversarial

    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
    ьо
    0.70
     빌
    0.69
     Car
    0.69
     Muc
    0.67
    뎐
    0.67
    ฬ
    0.67
    ığ
    0.64
    ஜா
    0.64
    山の
    0.63
     款
    0.63
    POSITIVE LOGITS
    Stand
    0.74
    olines
    0.67
    Squared
    0.65
     соли
    0.63
    ATP
    0.62
    Ꭴ
    0.62
    Accom
    0.62
    ócz
    0.62
     stali
    0.62
    Ад
    0.61
    Activations Density 0.003%

    No Known Activations