© 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. 697
    Prev
    Next
    INDEX
    Explanations

    unicode literals and trademarks

    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
     Broadcast
    -0.72
     verificación
    -0.71
    衣服
    -0.68
     सत्या
    -0.67
    neutral
    -0.67
     CONCLUS
    -0.65
    getBase
    -0.65
    庠
    -0.63
     Keb
    -0.62
     Stel
    -0.62
    POSITIVE LOGITS
     визу
    0.73
     ज्ञ
    0.72
     вас
    0.68
     fines
    0.68
    🇷
    0.67
    lacian
    0.67
    ooper
    0.66
     трав
    0.66
    кість
    0.66
    licet
    0.65
    Activations Density 0.065%

    No Known Activations