© 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. 39934
    Prev
    Next
    INDEX
    Explanations

    after code or numbers

    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
     POSITIVE
    -1.04
     dette
    -0.98
     konkrete
    -0.96
     visuel
    -0.96
    originally
    -0.93
    辈
    -0.92
     méda
    -0.91
    watched
    -0.91
     Logement
    -0.90
     legendar
    -0.90
    POSITIVE LOGITS
     demonstrated
    0.95
     would
    0.91
     as
    0.88
     could
    0.87
     strongly
    0.85
     demonstrating
    0.84
     certainly
    0.83
     massively
    0.81
     some
    0.81
     those
    0.81
    Activations Density 0.011%

    No Known Activations