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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 1894
    Prev
    Next
    INDEX
    Explanations

    multilingual characters

    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_17_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
    ので
    0.81
    st
    0.74
    ある
    0.73
    ity
    0.71
    heid
    0.69
    м
    0.69
    🙏🏻
    0.69
    an
    0.68
     pro
    0.68
     Fibonacci
    0.65
    POSITIVE LOGITS
    ме
    0.87
    assaytype
    0.84
    asikan
    0.82
    де
    0.80
    ⿹
    0.79
     exposureButton
    0.79
    бо
    0.78
    Υ
    0.78
    Ι
    0.78
    IONAL
    0.76
    Activations Density 0.074%

    No Known Activations