© 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. 67502
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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
    _
    -1.78
    what
    -1.77
    when
    -1.66
    Using
    -1.65
     that
    -1.64
    Several
    -1.64
     using
    -1.63
    Some
    -1.61
    During
    -1.59
    and
    -1.56
    POSITIVE LOGITS
    </em>
    2.27
    </h2>
    2.16
    をはじめ
    1.88
     are
    1.85
     Saltar
    1.79
    でしょうね
    1.70
    垢
    1.67
     was
    1.66
     primero
    1.65
    がありますが
    1.62
    Activations Density 0.022%

    No Known Activations