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. 47234
    Prev
    Next
    INDEX
    Explanations

    feminine tone, human reactions

    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
    ル
    0.92
    ەن
    0.91
    豪华
    0.89
    医师
    0.89
    けど
    0.87
    \|\
    0.87
    ლე
    0.86
     पेशेवर
    0.85
    ,$$
    0.84
    ://${
    0.82
    POSITIVE LOGITS
    achievement
    1.18
    𝐦
    1.18
     inauguration
    1.16
    𝐤
    1.14
    surge
    1.12
     सप्त
    1.12
     annulus
    1.10
     uji
    1.09
     achievement
    1.09
    svr
    1.08
    Activations Density 0.002%

    No Known Activations