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

    Neuronpedia

    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. 8962
    Prev
    Next
    INDEX
    Explanations

    feature or feature-rich

    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
    л
    4.98
    ة
    4.16
    ת
    4.11
    us
    3.75
    가
    3.49
    es
    3.38
    ه
    3.36
    т
    3.22
    i
    3.16
    o
    3.06
    POSITIVE LOGITS
     prominently
    5.54
    اً
    3.24
    fulness
    3.16
    tte
    3.10
    ்
    2.88
    erd
    2.85
    ствовал
    2.83
    y
    2.77
    FUL
    2.77
     chast
    2.72
    Activations Density 0.061%

    No Known Activations