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. 1961
    Prev
    Next
    INDEX
    Explanations

    recording filtered

    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
     Lake
    0.46
    各种
    0.45
     את
    0.44
     Seiten
    0.43
     तालिका
    0.43
     U
    0.43
    各式
    0.42
     F
    0.42
     T
    0.41
    Lake
    0.41
    POSITIVE LOGITS
     rather
    0.87
     chứ
    0.78
    而不是
    0.76
    rather
    0.75
    的一种
    0.73
    而非
    0.72
     insofar
    0.67
     وليس
    0.65
     encased
    0.64
    的一部分
    0.63
    Activations Density 1.493%

    No Known Activations