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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-65K
    4. 2128
    Prev
    Next
    INDEX
    Explanations

    describing where or how

    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
     inp
    1.35
     Computers
    1.28
     nonstop
    1.21
     oblige
    1.19
     ✓
    1.18
     cuy
    1.17
     thym
    1.17
     Tomatoes
    1.17
     acetic
    1.17
     hymns
    1.15
    POSITIVE LOGITS
    наў
    1.73
    ي
    1.45
    й
    1.35
    ர்
    1.34
    at
    1.33
    ת
    1.24
    anego
    1.21
    forc
    1.20
    ığı
    1.20
    াল
    1.18
    Activations Density 0.000%

    No Known Activations