© 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. 110587
    Prev
    Next
    INDEX
    Explanations

    Will followed by names or actions

    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
     are
    -2.59
    ↵
    -2.44
    淙
    -2.42
     escuchadas
    -2.41
    淅
    -2.39
    Ꝑ
    -2.39
    嘈
    -2.38
     offerings
    -2.38
     continúas
    -2.36
    
    -2.33
    POSITIVE LOGITS
    2
    2.97
    1
    2.91
     Will
    2.89
    ༴
    2.69
     για
    2.67
    oughby
    2.64
    頗
    2.63
     Our
    2.61
    );
    2.59
     "";
    2.44
    Activations Density 0.005%

    No Known Activations