© 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. 79726
    Prev
    Next
    INDEX
    Explanations

    mathematical and abstract concepts

    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
     misterioso
    -1.46
    Cierre
    -1.45
     brillant
    -1.44
     スリーブ
    -1.42
    .../
    -1.41
    ⁉
    -1.41
     côtes
    -1.39
     itinéraires
    -1.38
     nuages
    -1.38
    <bos>
    -1.37
    POSITIVE LOGITS
     we
    1.92
     their
    1.84
     there
    1.71
     even
    1.70
     our
    1.66
     each
    1.61
     with
    1.52
     like
    1.50
     now
    1.44
    情形
    1.39
    Activations Density 0.065%

    No Known Activations