© 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. 19455
    Prev
    Next
    INDEX
    Explanations

    amenities or amenorrhea

    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
    猻
    -2.63
    ি
    -2.61
    iocene
    -2.41
     Dritten
    -2.41
     специалистов
    -2.39
    alakip
    -2.39
     avec
    -2.36
    蕷
    -2.34
    texttt
    -2.28
    an
    -2.27
    POSITIVE LOGITS
    芣
    2.98
    ↵↵
    2.89
    鈇
    2.34
     jika
    2.31
    These
    2.25
     contento
    2.19
    This
    2.14
    >
    2.11
     tuve
    2.09
    珦
    2.08
    Activations Density 0.002%

    No Known Activations