© 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. 9-GEMMASCOPE-2-RES-16K
    7. 89
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     отношение
    1.56
    Се
    1.53
    ்கு
    1.50
     darüber
    1.44
    あとは
    1.36
     erkannt
    1.34
    প
    1.32
     находиться
    1.31
     kwargs
    1.30
    from
    1.29
    POSITIVE LOGITS
    ن
    1.81
    en
    1.70
    tedir
    1.55
     щодо
    1.55
    TOT
    1.39
    ന
    1.39
    тування
    1.39
    ν
    1.38
    }$\
    1.38
    nung
    1.38
    Activations Density 5.018%

    No Known Activations