© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110678
    Prev
    Next
    INDEX
    Explanations

    specific words followed by common words

    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
     marche
    -0.85
    彫刻
    -0.75
     ногтей
    -0.74
     دانش
    -0.73
     sombr
    -0.73
     recta
    -0.72
     divertir
    -0.72
     triom
    -0.71
    だったり
    -0.71
     comeback
    -0.71
    POSITIVE LOGITS
     fram
    0.78
    isSuccessful
    0.75
    ıştır
    0.74
    NOR
    0.73
     bibliographical
    0.73
     natal
    0.72
    ígeno
    0.71
    ਫ
    0.71
    표
    0.71
     壁
    0.71
    Activations Density 0.109%

    No Known Activations