© 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. 8861
    Prev
    Next
    INDEX
    Explanations

    historical context, significance, and accuracy

    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
    व
    1.08
    ą
    1.04
    в
    1.04
    Ciudad
    1.01
     doar
    1.00
     toán
    0.99
     것처럼
    0.98
    ্স
    0.98
    ่น
    0.97
    toothbrush
    0.96
    POSITIVE LOGITS
    т
    1.99
    ت
    1.76
    ০
    1.63
    ా
    1.60
    es
    1.53
    aa
    1.51
    aient
    1.49
    ی
    1.48
    িয়া
    1.48
    sat
    1.40
    Activations Density 0.128%

    No Known Activations