© 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. 85216
    Prev
    Next
    INDEX
    Explanations

    foreign language words and technical 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_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
    0
    -2.95
    ".
    -2.77
    hline
    -2.70
    O
    -2.61
    および
    -2.52
     —
    -2.42
    .”
    -2.41
    ."
    -2.41
    $-
    -2.41
    cdot
    -2.38
    POSITIVE LOGITS
    鈇
    3.13
    噲
    2.95
    boneca
    2.67
     abbildung
    2.63
    乆
    2.61
    衚
    2.59
    到处
    2.42
     wunderbar
    2.41
     kabar
    2.41
     estrellas
    2.41
    Activations Density 0.003%

    No Known Activations