© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10450
    Prev
    Next
    INDEX
    Explanations

    promote, promoting, promising

    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_9_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
    2.60
    pra
    2.55
    {'
    2.53
    г
    2.49
    ا
    2.46
     meantime
    2.37
    ⅼ
    2.37
    ñez
    2.35
    liu
    2.34
    چ
    2.34
    POSITIVE LOGITS
    र
    3.72
    restart
    3.37
    ро
    3.05
    
    2.94
    ৭১
    2.80
    ال
    2.78
    ेड
    2.71
    ы
    2.67
    ০০
    2.61
    améli
    2.61
    Activations Density 0.091%

    No Known Activations