© 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. 104413
    Prev
    Next
    INDEX
    Explanations

    Product development

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of non‐ASCII characters (accented or special Unicode letters) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     for
    -1.98
    );
    -1.94
    -
    -1.91
    ő
    -1.72
     unrelenting
    -1.71
     If
    -1.70
    ;
    -1.70
     :
    -1.67
     Despite
    -1.66
     ;
    -1.62
    POSITIVE LOGITS
    神
    2.08
    킁
    1.93
    oused
    1.91
    峮
    1.88
    擼
    1.86
    褙
    1.81
     they
    1.80
    tiness
    1.77
    搋
    1.75
     mesures
    1.74
    Activations Density 0.001%

    No Known Activations