© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35447
    Prev
    Next
    INDEX
    Explanations

    geographical terms and foreign languages

    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
    Not in Any Lists

    No Comments

    Negative Logits
    These
    -1.21
    いろんな
    -1.10
     gewährle
    -1.08
    This
    -1.03
     сообщили
    -0.99
     拖
    -0.99
    関連リンク
    -0.98
     Очень
    -0.97
     erstre
    -0.97
    のでしょう
    -0.97
    POSITIVE LOGITS
     maïs
    1.08
     into
    1.07
     ихъ
    1.05
     листь
    1.05
     coloridas
    1.05
    bestand
    1.03
    Географи
    1.02
     dör
    1.02
     Certificado
    1.01
     देखें
    0.98
    Activations Density 0.025%

    No Known Activations