© 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. 84946
    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
     andato
    -1.02
    นอก
    -0.96
     riuscito
    -0.96
    橚
    -0.94
    föl
    -0.93
     onore
    -0.93
    ”;
    -0.92
    Қ
    -0.91
     tinta
    -0.91
     misericordia
    -0.91
    POSITIVE LOGITS
    ventud
    1.07
    KommentareTeilen
    1.02
    ৳
    0.98
     kleiner
    0.95
    芮
    0.94
     regulación
    0.91
     meditación
    0.91
     (*)
    0.91
     '(
    0.90
    corona
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.