© 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. 22-GEMMASCOPE-2-RES-16K
    7. 511
    Prev
    Next
    INDEX
    Explanations

    geographical names and languages

    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_22_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
    0.84
    es
    0.54
    er
    0.54
    ,
    0.52
    os
    0.50
    oretically
    0.50
     of
    0.50
    en
    0.49
     to
    0.48
    ي
    0.47
    POSITIVE LOGITS
    Depois
    0.66
    ക്കുറിച്ച്
    0.63
    ên
    0.62
    Three
    0.60
    ૦
    0.60
    ńskiej
    0.60
    Communications
    0.58
    Nome
    0.58
    <unused377>
    0.57
    Κ
    0.57
    Activations Density 0.616%

    No Known Activations