© 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. 29-GEMMASCOPE-2-RES-262K
    7. 148865
    Prev
    Next
    INDEX
    Explanations

    salary slips

    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_29_width_262k_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
     মনোযোগ
    0.96
     замет
    0.96
     Ajouter
    0.94
    重點
    0.90
     étendue
    0.89
     reforzar
    0.88
    ларни
    0.86
    辎
    0.85
    犒
    0.85
     Ahmad
    0.84
    POSITIVE LOGITS
    so
    0.79
    ↵↵
    0.70
    der
    0.70
    pem
    0.66
     ওঠার
    0.64
    ிருப்ப
    0.64
    Is
    0.64
    erta
    0.64
    nesses
    0.63
    Um
    0.62
    Activations Density 0.001%

    No Known Activations