© 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. 75155
    Prev
    Next
    INDEX
    Explanations

    describing specific features or deviations

    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
    毌
    -1.32
     qualsiasi
    -1.23
     necessary
    -1.22
     aziende
    -1.22
     progettazione
    -1.21
     geene
    -1.20
    Historio
    -1.20
     পার
    -1.17
    ྥ
    -1.17
     lte
    -1.16
    POSITIVE LOGITS
     two
    1.63
     a
    1.45
    らかに
    1.38
     an
    1.25
     "
    1.22
     не
    1.20
     four
    1.17
     three
    1.15
     split
    1.14
    idelberg
    1.14
    Activations Density 0.244%

    No Known Activations