© 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. 22-GEMMASCOPE-RES-131K
    7. 98454
    Prev
    Next
    INDEX
    Explanations

    mathematical or code variable r

    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_22/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
    e
    -2.77
    y
    -2.63
     дуже
    -2.56
     моя
    -2.52
    <bos>
    -2.47
    为什么
    -2.38
    g
    -2.38
    s
    -2.34
     вопро
    -2.30
    ússia
    -2.30
    POSITIVE LOGITS
    毟
    2.70
    睺
    2.33
    ’
    2.30
    尖叫
    2.23
    妧
    2.22
    匐
    2.19
    those
    2.16
    鲠
    2.14
    凄い
    2.09
    匆
    2.08
    Activations Density 0.130%

    No Known Activations