© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75357
    Prev
    Next
    INDEX
    Explanations

    delimiters and separators

    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
    :''
    -1.95
    plz
    -1.87
    )‏
    -1.82
    🤢
    -1.79
    …»
    -1.77
    ELTS
    -1.74
     ír
    -1.71
    :[]
    -1.71
     ögon
    -1.71
    ̕
    -1.70
    POSITIVE LOGITS
     there
    2.09
     such
    2.06
     unlike
    2.03
     owing
    1.99
     like
    1.91
     Gesund
    1.68
     they
    1.67
    ⃕
    1.57
     everything
    1.57
     thereby
    1.55
    Activations Density 0.001%

    No Known Activations