© 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. 131015
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Honestly
    -1.41
     When
    -1.37
     Giving
    -1.33
     their
    -1.32
     Give
    -1.27
     by
    -1.27
    6
    -1.26
     Extremely
    -1.23
     Eight
    -1.22
     nearing
    -1.20
    POSITIVE LOGITS
    ſſen
    1.91
     pertinente
    1.61
     suí
    1.54
    ᕱ
    1.52
    ୮
    1.47
    ⚥
    1.47
    珹
    1.44
     mici
    1.43
    ⚊
    1.43
     grote
    1.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.