© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66673
    Prev
    Next
    INDEX
    Explanations

    sheet following words

    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
    ⡪
    -2.47
    缡
    -2.47
     哪些
    -2.41
     asamblea
    -2.39
    UNTAIN
    -2.30
    ⢌
    -2.28
    些什么
    -2.27
    憷
    -2.25
    
    -2.25
     arbres
    -2.19
    POSITIVE LOGITS
    '
    4.72
     This
    2.92
    With
    2.84
    You
    2.70
    What
    2.63
    你不是
    2.47
    」,
    2.42
     verschied
    2.39
    (
    2.36
    可以
    2.34
    Activations Density 0.012%

    No Known Activations