© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180228
    Prev
    Next
    INDEX
    Explanations

    Meta data

    np_acts-logits-general · gemini-2.5-flash-lite

    defining concepts and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ២
    0.52
    nonzero
    0.52
    يرة
    0.50
    伱
    0.47
    箭
    0.47
    提
    0.46
    泡
    0.46
    舔
    0.46
     confounded
    0.45
    كره
    0.45
    POSITIVE LOGITS
    วา
    0.51
    รือ
    0.50
     guru
    0.49
    iy
    0.48
     seseorang
    0.48
     เรียก
    0.47
     distribut
    0.47
     sofr
    0.47
    잠
    0.47
     distribution
    0.46
    Activations Density 0.000%

    No Known Activations