© 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. 10-GEMMASCOPE-RES-131K
    7. 127190
    Prev
    Next
    INDEX
    Explanations

    allows to [verb]

    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_10/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
    f
    -2.11
    ،
    -1.96
    c
    -1.92
    on
    -1.80
     Risiken
    -1.78
     diyor
    -1.78
     Corollary
    -1.74
    4
    -1.73
    »,
    -1.72
     और
    -1.70
    POSITIVE LOGITS
    ichtete
    2.36
     and
    2.19
    ichteten
    2.08
     used
    1.88
    loped
    1.78
     redenen
    1.77
     primit
    1.77
     OGSÅ
    1.76
     aplicable
    1.76
     soorten
    1.75
    Activations Density 0.003%

    No Known Activations