© 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. 560
    Prev
    Next
    INDEX
    Explanations

    surfing and associated terms

    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
    場合には
    -1.42
     the
    -1.40
    ほら
    -1.24
     Paths
    -1.23
    expiresIn
    -1.20
     aktiviert
    -1.20
    ሥ
    -1.20
     食器
    -1.19
    ră
    -1.18
    ものに
    -1.16
    POSITIVE LOGITS
     wave
    1.33
    isição
    1.23
    ྃ
    1.20
    чения
    1.19
    ॰
    1.19
    addTab
    1.16
    oudoune
    1.16
     mágica
    1.16
     anglès
    1.16
     cualquier
    1.15
    Activations Density 0.023%

    No Known Activations