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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103092
    Prev
    Next
    INDEX
    Explanations

    places names like Belleville or Maastricht

    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
    Not in Any Lists

    No Comments

    Negative Logits
    startY
    -0.78
    retum
    -0.77
     coc
    -0.75
    Història
    -0.74
     tus
    -0.74
    yari
    -0.73
    持有
    -0.73
     paddles
    -0.73
    直し
    -0.72
    Törté
    -0.71
    POSITIVE LOGITS
     Belleville
    0.80
     Kapoor
    0.80
    чности
    0.77
     μην
    0.69
    pantaloni
    0.69
    ofern
    0.68
    མ
    0.66
    ルール
    0.65
     Annex
    0.65
     Cheyenne
    0.65
    Activations Density 0.009%

    No Known Activations