© 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. 38778
    Prev
    Next
    INDEX
    Explanations

    c, r, ge, j url beginnings

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

    github.com/ user/repo

    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
    蠵
    0.55
    ⬯
    0.52
    䋇
    0.50
    llrp
    0.49
    カウン
    0.48
    ครื่อง
    0.47
     DISPLAYSURF
    0.46
     фотоап
    0.46
    𒌦
    0.46
    钨
    0.46
    POSITIVE LOGITS
    ik
    0.70
    o
    0.69
    q
    0.66
    ini
    0.65
    aj
    0.65
    y
    0.64
    ina
    0.62
    ami
    0.62
    ie
    0.61
    m
    0.61
    Activations Density 0.000%

    No Known Activations