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. 47102
    Prev
    Next
    INDEX
    Explanations

    differential calculus and integrals

    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
    oyl
    0.92
    暗
    0.86
    nın
    0.86
    ૫
    0.80
     formulas
    0.80
    י
    0.79
    n
    0.78
    BrN
    0.77
     boardroom
    0.77
     bam
    0.77
    POSITIVE LOGITS
     prospecting
    0.99
    িক্ষে
    0.96
    過ご
    0.94
    udy
    0.91
     trifling
    0.91
     lluv
    0.91
     europeos
    0.87
     Ugar
    0.86
     металла
    0.86
    ﻵ
    0.85
    Activations Density 0.036%

    No Known Activations