© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30094
    Prev
    Next
    INDEX
    Explanations

    PHP session and request variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    rieren
    -0.77
     tic
    -0.72
     البد
    -0.70
    血压
    -0.70
     Nach
    -0.69
    brando
    -0.68
    yyah
    -0.68
    信
    -0.68
    cích
    -0.68
    xymatrix
    -0.67
    POSITIVE LOGITS
     session
    2.83
     Session
    2.66
    Session
    2.59
    session
    2.55
    SESSION
    2.38
     SESSION
    2.30
     sessions
    2.20
     Sessions
    2.03
     $_
    1.98
    =$_
    1.90
    Activations Density 0.115%

    No Known Activations