© 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. 13143
    Prev
    Next
    INDEX
    Explanations

    Vermont or numbers followed by punctuation

    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
     any
    -0.84
    ldern
    -0.81
     jangka
    -0.79
    깅
    -0.78
     DirectX
    -0.76
     Hände
    -0.75
     them
    -0.73
     gants
    -0.72
    켜
    -0.72
    とりあえず
    -0.71
    POSITIVE LOGITS
    玙
    0.97
    ourcen
    0.95
    irled
    0.93
    ΗΣ
    0.92
    cipated
    0.92
    粱
    0.92
    FindBy
    0.91
    赑
    0.91
    ächlich
    0.90
    chable
    0.89
    Activations Density 0.005%

    No Known Activations