© 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. 34-GEMMASCOPE-RES-131K
    4. 119376
    Prev
    Next
    INDEX
    Explanations

    educational processes and software

    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_34/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
    眼底
    -0.84
     bå
    -0.83
     salat
    -0.77
     maksimal
    -0.75
     opere
    -0.75
    🐤
    -0.75
    戰鬥
    -0.74
     Leck
    -0.74
    versed
    -0.74
     vuelos
    -0.74
    POSITIVE LOGITS
    监控
    0.98
     system
    0.86
    peda
    0.85
    Dimension
    0.82
     modern
    0.82
    }-
    0.81
     système
    0.81
    Coun
    0.79
     metas
    0.77
    返信
    0.76
    Activations Density 0.003%

    No Known Activations