© 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. 10-GEMMASCOPE-RES-131K
    7. 18969
    Prev
    Next
    INDEX
    Explanations

    CA certificate authority

    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_10/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
     такие
    -1.43
     altres
    -1.43
    '
    -1.42
    geordnet
    -1.37
     eindeutig
    -1.37
     horrible
    -1.35
    戥
    -1.32
     такой
    -1.31
     тези
    -1.30
    ᗯ
    -1.30
    POSITIVE LOGITS
    ()]);
    1.59
     From
    1.50
    炱
    1.35
    hlands
    1.34
     While
    1.30
    ディース
    1.29
    hiva
    1.29
    ܃
    1.28
    zied
    1.28
    Ты
    1.27
    Activations Density 0.010%

    No Known Activations