© 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. 124726
    Prev
    Next
    INDEX
    Explanations

    temptation and calm

    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
    In
    -3.05
    
    -2.88
    ஂ
    -2.86
    On
    -2.73
    Most
    -2.58
    If
    -2.53
    Now
    -2.39
    All
    -2.39
     \
    -2.38
    Since
    -2.36
    POSITIVE LOGITS
    嗫
    3.03
    逦
    2.97
     apont
    2.92
     They
    2.84
     acrescent
    2.78
     Externe
    2.77
     Their
    2.73
    archiwizowane
    2.70
     desempen
    2.67
     fornecer
    2.66
    Activations Density 0.002%

    No Known Activations