© 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. 9-GEMMASCOPE-2-RES-262K
    7. 10414
    Prev
    Next
    INDEX
    Explanations

    dopamine and reinforcement learning

    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_9_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
    ">\
    1.56
     chino
    1.54
     imgSrc
    1.54
     gloria
    1.52
     nay
    1.51
    ಛ
    1.51
     blanket
    1.50
     getImage
    1.48
     getDateTime
    1.48
     caldo
    1.47
    POSITIVE LOGITS
    hitva
    2.02
    ময়
    1.97
    ت
    1.79
    اب
    1.71
    ال
    1.69
    ᴀ
    1.63
     menjalani
    1.63
    ymmetric
    1.62
    ké
    1.61
    tól
    1.56
    Activations Density 0.057%

    No Known Activations