© 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. 68432
    Prev
    Next
    INDEX
    Explanations

    impact on or of

    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
    of
    -2.42
    The
    -2.39
    姈
    -2.13
     poate
    -2.03
    tences
    -2.02
    ."
    -1.98
     molti
    -1.97
    ностях
    -1.97
    再一次
    -1.95
     focussed
    -1.94
    POSITIVE LOGITS
    ஂ
    3.30
    柃
    2.47
    𓍊
    2.31
    嗞
    2.23
    𖥦
    2.19
    グルト
    2.17
    tempat
    2.13
     مدیریت
    2.02
    
    1.97
    
    1.95
    Activations Density 0.015%

    No Known Activations