© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3610
    Prev
    Next
    INDEX
    Explanations

    science, code, or polish language phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    栃
    0.85
     सेलिब्र
    0.84
     Chuk
    0.81
    br
    0.81
     ধ্ব
    0.80
     ইংরা
    0.79
     compétence
    0.75
    鄞
    0.74
     Progn
    0.74
    char
    0.73
    POSITIVE LOGITS
     Dyson
    0.96
     Muz
    0.95
     Forest
    0.95
     Wilcox
    0.92
     Palace
    0.91
     Anaconda
    0.91
     Musa
    0.90
     Hef
    0.88
     Frazier
    0.88
     Belvedere
    0.88
    Activations Density 0.765%

    No Known Activations