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. 513
    Prev
    Next
    INDEX
    Explanations

    running simulations

    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
    Го
    0.89
    Со
    0.86
     例文帳に追加
    0.86
    黉
    0.83
     Львів
    0.81
    >`,
    0.80
    Công
    0.79
    <unused86>
    0.79
    <unused50>
    0.78
    靣
    0.78
    POSITIVE LOGITS
     bring
    0.81
     blood
    0.80
     smart
    0.78
     find
    0.76
     raise
    0.76
     run
    0.69
     remind
    0.68
     threading
    0.67
     glad
    0.66
     spots
    0.66
    Activations Density 0.000%

    No Known Activations