© 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. 103523
    Prev
    Next
    INDEX
    Explanations

    copyright notice and disclaimer

    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
     Архи
    -0.75
    ameter
    -0.71
    brooks
    -0.70
    胄
    -0.69
    Executors
    -0.69
    Loy
    -0.68
     Legendre
    -0.67
     Judo
    -0.66
    existsSync
    -0.66
    抽選
    -0.66
    POSITIVE LOGITS
     restrain
    0.75
     Vare
    0.71
    rable
    0.67
     QString
    0.67
    automat
    0.66
    ohyd
    0.66
    Ziel
    0.66
     постав
    0.66
    ograf
    0.65
     unaweza
    0.65
    Activations Density 0.060%

    No Known Activations