© 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. 9123
    Prev
    Next
    INDEX
    Explanations

    comparisons and quantities

    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
     যশোরের
    0.95
    寜
    0.95
     delete
    0.94
     મોત
    0.91
     eternity
    0.91
    মন্ত্রীর
    0.91
    飾り
    0.90
     étoile
    0.89
     saisons
    0.89
     cartilage
    0.88
    POSITIVE LOGITS
    ות
    1.02
    preset
    0.90
    een
    0.85
    hc
    0.82
    angel
    0.82
    iembre
    0.81
    ו
    0.81
    yun
    0.81
    tc
    0.80
    לא
    0.78
    Activations Density 0.000%

    No Known Activations