© 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. 1030
    Prev
    Next
    INDEX
    Explanations

    of [noun phrase]

    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
     anstatt
    -1.54
     numai
    -1.53
    the
    -1.52
     bénéficie
    -1.52
     reforzar
    -1.48
     apoyar
    -1.44
    جانب
    -1.43
    ьет
    -1.42
     squal
    -1.42
    点点头
    -1.41
    POSITIVE LOGITS
    ’
    1.87
     ignite
    1.60
     verlangen
    1.56
     these
    1.55
     a
    1.43
     cripple
    1.38
    ций
    1.36
    поги
    1.34
     this
    1.31
     Anche
    1.31
    Activations Density 0.031%

    No Known Activations