© 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. 69402
    Prev
    Next
    INDEX
    Explanations

    woods

    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
    鰾
    -3.13
    e
    -2.91
    齪
    -2.77
    鶉
    -2.56
    饪
    -2.53
    焄
    -2.52
    檍
    -2.42
    歛
    -2.42
    鈰
    -2.38
    皤
    -2.36
    POSITIVE LOGITS
     
    2.94
    .
    2.81
     esche
    2.67
    事も
    2.55
    They
    2.50
    Amid
    2.50
    嘞
    2.48
    This
    2.44
    ON
    2.42
    慎重
    2.39
    Activations Density 0.002%

    No Known Activations