© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14940
    Prev
    Next
    INDEX
    Explanations

    code comments after symbols

    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_16k_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
    ۰
    0.98
    <unused967>
    0.96
    ாளையம்
    0.92
    ل
    0.88
     وړاندوین
    0.88
    <unused937>
    0.87
    nvim
    0.86
    <unused1068>
    0.86
    DrawerToggle
    0.85
     والم
    0.85
    POSITIVE LOGITS
     heel
    1.03
     pihaknya
    0.94
     heels
    0.92
     muestra
    0.92
     bazı
    0.91
    実際に
    0.90
     quarts
    0.89
     aton
    0.89
     mesin
    0.89
     Украине
    0.88
    Activations Density 0.008%

    No Known Activations