Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 19512
    Prev
    Next
    INDEX
    Explanations

    system of equations

    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_22_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
     спраши
    0.71
     जवाब
    0.70
    terdam
    0.66
    (_,
    0.65
     القاعد
    0.63
     Asked
    0.63
    isodes
    0.60
     ഇത്തരം
    0.59
     پوچھا
    0.59
     случаев
    0.59
    POSITIVE LOGITS
    <unused2162>
    0.86
     below
    0.81
     firstly
    0.80
     packer
    0.79
    这里
    0.78
     দুইটি
    0.77
    orne
    0.77
     选择
    0.77
     determine
    0.76
    有两个
    0.75
    Activations Density 0.015%

    No Known Activations