© 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. 81397
    Prev
    Next
    INDEX
    Explanations

    surnames followed by places and institutions

    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
    ynthesis
    -1.01
    տ
    -1.01
    tu
    -0.98
    cheduling
    -0.95
    ta
    -0.91
    tole
    -0.90
    iz
    -0.90
    to
    -0.90
     recomendado
    -0.90
    tre
    -0.88
    POSITIVE LOGITS
    ons
    1.18
     Sonoma
    1.00
    AutoresizingMask
    0.98
    '}
    0.93
    </h3>
    0.93
    られて
    0.92
     礼物
    0.91
    gesterone
    0.91
    '>
    0.90
    INDICATOR
    0.90
    Activations Density 0.061%

    No Known Activations