© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2085
    Prev
    Next
    INDEX
    Explanations

    family relations, code arrays, variety

    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_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
    ان
    5.11
    ר
    4.81
    ১
    4.79
    र
    4.35
    р
    4.29
    ق
    4.13
    an
    3.84
    
    3.76
    с
    3.65
     seva
    3.65
    POSITIVE LOGITS
    ا
    4.13
    𝙝
    3.96
    й
    3.91
    𝙩
    3.91
    𝙣
    3.75
    ি
    3.67
    𝙜
    3.54
    𝙨
    3.53
    ள்ள
    3.45
    𝙤
    3.42
    Activations Density 0.877%

    No Known Activations