© 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. 2333
    Prev
    Next
    INDEX
    Explanations

    user prompts for tasks

    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
     สำหรับ
    0.91
    _
    0.91
     Profile
    0.90
    ufthansa
    0.84
     nhé
    0.84
     Profiles
    0.82
     sont
    0.81
     Specification
    0.81
     critique
    0.81
     specification
    0.80
    POSITIVE LOGITS
    miy
    0.94
    कई
    0.93
    வீன
    0.93
    tans
    0.93
    毛
    0.92
    thed
    0.91
    None
    0.91
    បង្ហ
    0.91
    每天
    0.90
    Ⲱ
    0.90
    Activations Density 0.000%

    No Known Activations