© 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. 246996
    Prev
    Next
    INDEX
    Explanations

    making things like connection, site, or paper

    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
    YOUR
    0.47
    閆
    0.45
    現實
    0.43
    上述
    0.43
    類似
    0.41
    敺
    0.41
    秀
    0.41
    債
    0.41
    ారణ
    0.40
    你們
    0.40
    POSITIVE LOGITS
     ine
    0.50
     apologizing
    0.48
    aves
    0.47
     więcej
    0.47
     niej
    0.46
     ज़्यादा
    0.46
     hicieron
    0.46
     officially
    0.46
     inept
    0.46
     inaccur
    0.46
    Activations Density 0.001%

    No Known Activations