© 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. 22-GEMMASCOPE-RES-131K
    7. 127839
    Prev
    Next
    INDEX
    Explanations

    algebraic and function expressions

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     their
    -1.20
     fueron
    -1.09
     especialmente
    -1.06
    nhà
    -1.00
    =""/>
    -0.98
    ைய
    -0.96
    Več
    -0.94
     vervolgens
    -0.94
    giai
    -0.93
     with
    -0.93
    POSITIVE LOGITS
    Muchas
    0.96
    “……”
    0.88
     épices
    0.88
    according
    0.88
    Beijinhos
    0.85
    ブーツ
    0.85
    Pantalla
    0.84
    进入了
    0.83
    沒有
    0.82
    スプレー
    0.82
    Activations Density 0.005%

    No Known Activations