© 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-65K
    7. 1165
    Prev
    Next
    INDEX
    Explanations

    letter options and identifiers

    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_65k_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
    a
    0.73
    e
    0.63
     GPU
    0.60
    tage
    0.58
    er
    0.57
     ginger
    0.57
     Julie
    0.56
    s
    0.56
     SGD
    0.54
     CTO
    0.54
    POSITIVE LOGITS
    З
    0.69
    За
    0.68
    Quantidade
    0.64
    ANG
    0.63
    ۶
    0.62
    Z
    0.62
    Quem
    0.61
    Какие
    0.61
    इससे
    0.61
    यह
    0.60
    Activations Density 0.706%

    No Known Activations