© 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. 173840
    Prev
    Next
    INDEX
    Explanations

    linking to creation

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

    reentrancy, repeating mistakes, parallel path

    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
    Not in Any Lists

    No Comments

    Negative Logits
    agn
    0.48
    foods
    0.46
    ?
    0.46
     fussy
    0.46
     kıl
    0.45
    quers
    0.45
     armature
    0.44
     organizes
    0.44
     maxillary
    0.43
    *
    0.43
    POSITIVE LOGITS
     सत्या
    0.54
    ሒ
    0.50
     เนื่อง
    0.49
    化工
    0.49
     मेहनत
    0.48
     लगाकर
    0.48
     ché
    0.48
    重庆
    0.47
    పర
    0.47
     แถม
    0.47
    Activations Density 0.001%

    No Known Activations