© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 16323
    Prev
    Next
    INDEX
    Explanations

    package contents or management

    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
     불구하고
    2.78
    らえる
    2.74
    یه
    2.68
    ến
    2.60
    െയി
    2.58
     불구
    2.46
    asd
    2.41
    
    2.39
    輒
    2.36
    耄
    2.34
    POSITIVE LOGITS
    袱
    3.39
    拯
    3.14
     morto
    2.99
    م
    2.95
     nhiêu
    2.94
    simeq
    2.91
    ಯಲ್ಲಿ
    2.83
     SafeArea
    2.83
     baterías
    2.64
    ள்ளது
    2.63
    Activations Density 0.107%

    No Known Activations