© 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. 79389
    Prev
    Next
    INDEX
    Explanations

    economic crisis, estate slump, version speaks

    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
    вич
    -0.78
     Και
    -0.77
    nearly
    -0.76
    евна
    -0.76
    Fingerprint
    -0.75
     艾
    -0.74
    several
    -0.73
    ׇ
    -0.71
    session
    -0.71
     भार
    -0.71
    POSITIVE LOGITS
    ּוֹ
    0.95
    рецепт
    0.93
    choc
    0.91
     takeoff
    0.84
    Mich
    0.84
    埔
    0.83
    牧
    0.82
    ְר
    0.82
    KATH
    0.82
     EVERYONE
    0.82
    Activations Density 0.003%

    No Known Activations