© 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-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 8173
    Prev
    Next
    INDEX
    Explanations

    close estimate

    np_max-act-logits · gemini-2.5-flash-lite

    close measurements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    delay
    0.55
    捻
    0.52
    document
    0.51
    有料
    0.50
    ritable
    0.49
    нк
    0.49
    ยก
    0.48
    லய
    0.48
    <0xDE>
    0.48
    Compared
    0.48
    POSITIVE LOGITS
     डब्ल्यू
    0.68
     Flav
    0.59
    otte
    0.57
     Chatt
    0.57
     भर्त
    0.57
    镑
    0.57
     Skyl
    0.57
     spoons
    0.56
     prezzo
    0.55
     مذہ
    0.55
    Activations Density 0.002%

    No Known Activations