© 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. 10178
    Prev
    Next
    INDEX
    Explanations

    HTML attributes or tags

    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
    eurs
    1.32
    eur
    1.28
    tional
    1.26
    yya
    1.19
     hany
    1.17
     vitally
    1.13
    猬
    1.12
     proper
    1.12
    ductory
    1.11
    ividual
    1.11
    POSITIVE LOGITS
    安い
    1.06
    inos
    1.00
    ধ
    0.96
    cols
    0.95
    に
    0.95
    rho
    0.94
     سوی
    0.91
     Diput
    0.91
    鍑
    0.90
    ع
    0.90
    Activations Density 0.001%

    No Known Activations