© 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. 20430
    Prev
    Next
    INDEX
    Explanations

    do you think

    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
    豋
    -1.81
     alcuni
    -1.80
     alcune
    -1.80
    much
    -1.79
     jejich
    -1.67
     molti
    -1.61
     niedersachsen
    -1.55
    unfortunately
    -1.55
     Dinas
    -1.54
     atmosfera
    -1.53
    POSITIVE LOGITS
     in
    1.98
     with
    1.93
     it
    1.91
     or
    1.80
     at
    1.77
     after
    1.73
     by
    1.72
     out
    1.66
     time
    1.58
     went
    1.52
    Activations Density 0.018%

    No Known Activations