© 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. 102484
    Prev
    Next
    INDEX
    Explanations

    creating table

    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
    waffe
    -0.82
    ঙ্গ
    -0.81
    🐊
    -0.81
     pouvoit
    -0.78
    üb
    -0.78
    muerzo
    -0.77
     acol
    -0.77
    ᭄
    -0.77
     pregnancies
    -0.75
     Volatility
    -0.75
    POSITIVE LOGITS
    Tables
    1.08
     tables
    1.05
     Tables
    0.91
    tables
    0.90
     TABLES
    0.84
     except
    0.81
     into
    0.81
    Exec
    0.77
    зу
    0.75
    tu
    0.74
    Activations Density 0.003%

    No Known Activations