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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 53046
    Prev
    Next
    INDEX
    Explanations

    apolipoproteins and lasagna

    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
     Olig
    0.80
     Tregs
    0.77
     Tags
    0.72
    FANG
    0.72
    UBE
    0.72
     lag
    0.72
     正
    0.71
    ube
    0.70
     dode
    0.70
     ugg
    0.68
    POSITIVE LOGITS
     రహ
    0.76
    ConfigSource
    0.71
    尒
    0.69
    ဖြစ်သည်။
    0.68
    mie
    0.67
    殻
    0.66
    צר
    0.65
    ซี
    0.65
    ⊷
    0.64
    ーストラリア
    0.64
    Activations Density 0.002%

    No Known Activations