© 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. 81192
    Prev
    Next
    INDEX
    Explanations

    license or import statements

    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
    onant
    -0.78
    liez
    -0.77
     paradigm
    -0.77
     Corr
    -0.75
    innan
    -0.74
     hjælpe
    -0.74
     first
    -0.73
     Basque
    -0.73
    ✶
    -0.71
    姣
    -0.71
    POSITIVE LOGITS
     atter
    0.88
    永久
    0.82
     моделей
    0.82
    应该
    0.81
    ――
    0.79
     Bengals
    0.79
    Allgeme
    0.79
     tuss
    0.79
    нализ
    0.79
     abd
    0.79
    Activations Density 0.001%

    No Known Activations