© 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-16K
    7. 10168
    Prev
    Next
    INDEX
    Explanations

    smooth factors perspectives

    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_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
     역시
    0.99
     处理
    0.90
     无
    0.82
     utilización
    0.81
    ষ্কৃত
    0.81
     Systeme
    0.81
     використа
    0.80
     بررسی
    0.80
    찬가지
    0.80
     utilização
    0.80
    POSITIVE LOGITS
     bling
    1.17
     "
    1.03
     leprosy
    0.94
     “
    0.93
     recipe
    0.91
     saying
    0.91
    pull
    0.89
     sexy
    0.89
     poking
    0.88
     guts
    0.88
    Activations Density 0.403%

    No Known Activations