© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 10883
    Prev
    Next
    INDEX
    Explanations

    emphasis on the thing itself

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <unused577>
    0.86
    <unused301>
    0.76
    ках
    0.71
    <unused2045>
    0.69
    ियोग्राफी
    0.69
    <unused1799>
    0.69
    elmi
    0.69
     concursos
    0.69
    <unused2145>
    0.68
    রামর্শ
    0.68
    POSITIVE LOGITS
     itself
    2.64
    本身
    2.15
    本身的
    1.95
     themselves
    1.74
     نفسها
    1.55
     자체
    1.55
    เอง
    1.51
     자체가
    1.49
    自体
    1.48
     itse
    1.42
    Activations Density 0.130%

    No Known Activations