© 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
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 150041
    Prev
    Next
    INDEX
    Explanations

    section numbers

    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
     joueurs
    0.85
    /−
    0.84
     szczegól
    0.84
     intenso
    0.83
     intensa
    0.82
    ához
    0.81
     ব্যস্ত
    0.80
    +(\
    0.80
     hometown
    0.79
     poucos
    0.79
    POSITIVE LOGITS
    idi
    0.69
    idio
    0.68
    Look
    0.67
    for
    0.66
    Legisl
    0.62
    Styles
    0.61
     Look
    0.61
    Nel
    0.61
    Sum
    0.60
    Air
    0.58
    Activations Density 0.004%

    No Known Activations