© 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. 513
    Prev
    Next
    INDEX
    Explanations

    variable assignment and data indexing

    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
     suplementos
    -1.35
    føre
    -1.20
     kağıdı
    -1.17
    얏
    -1.17
    ˛
    -1.16
     besø
    -1.14
     calorías
    -1.13
    ulating
    -1.13
     отсут
    -1.12
     remercie
    -1.11
    POSITIVE LOGITS
     our
    1.49
     now
    1.44
     these
    1.14
     even
    1.13
     just
    1.13
     new
    1.10
     eventually
    1.09
     only
    1.06
     of
    1.02
    下車
    1.02
    Activations Density 0.005%

    No Known Activations