© 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. 22-GEMMASCOPE-2-RES-262K
    7. 14272
    Prev
    Next
    INDEX
    Explanations

    Flask plus `(`

    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_22_width_262k_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
    в
    0.99
    ievements
    0.97
     aur
    0.96
     chemins
    0.96
     marinas
    0.95
     mercados
    0.89
     mercado
    0.89
    ηση
    0.87
     caoutch
    0.87
    вки
    0.86
    POSITIVE LOGITS
    (__
    1.34
     __
    1.12
     (__
    1.00
     ________
    0.94
     __________
    0.93
    __
    0.91
    ___
    0.89
     {});
    0.86
     ____
    0.86
     {})
    0.85
    Activations Density 0.007%

    No Known Activations