© 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. 22-GEMMASCOPE-RES-131K
    7. 13865
    Prev
    Next
    INDEX
    Explanations

    permission to act

    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
     some
    -1.16
    <bos>
    -1.05
    庭園
    -1.03
     poder
    -1.02
    :
    -0.97
    *}
    -0.96
     pouvoir
    -0.96
     maybe
    -0.95
     could
    -0.94
    titleLabel
    -0.94
    POSITIVE LOGITS
     only
    1.28
     любого
    1.27
     любой
    1.23
    Hanya
    1.16
     любое
    1.16
     qualquer
    1.16
     either
    1.15
    的最大
    1.15
     любы
    1.09
     dikatakan
    1.09
    Activations Density 0.091%

    No Known Activations