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-65K
    4. 1978
    Prev
    Next
    INDEX
    Explanations

    real-time gold price information

    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_65k_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
    ulière
    0.67
     `'\\
    0.67
    櫳
    0.66
     involunt
    0.65
    ută
    0.62
    🧾
    0.62
    芑
    0.62
    崠
    0.62
    ்கலை
    0.61
    िक्र
    0.61
    POSITIVE LOGITS
    8
    1.83
    5
    1.81
    7
    1.74
    6
    1.70
    4
    1.62
    9
    1.61
    0
    1.59
    3
    1.57
    2
    1.46
    1
    1.27
    Activations Density 0.808%

    No Known Activations