© 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. 17-GEMMASCOPE-2-RES-16K
    7. 9175
    Prev
    Next
    INDEX
    Explanations

    concentrating on specifics

    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
     ética
    1.00
    
    0.99
    nikom
    0.98
    urgo
    0.97
    ේශ
    0.97
    <unused497>
    0.97
     interdiscipl
    0.97
     historiques
    0.97
    iously
    0.96
     utvik
    0.96
    POSITIVE LOGITS
     غير
    0.87
    tidak
    0.79
     يا
    0.79
    To
    0.74
    ذن
    0.73
     Compute
    0.72
     nope
    0.72
    Or
    0.71
    return
    0.70
    또
    0.70
    Activations Density 0.077%

    No Known Activations