© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99671
    Prev
    Next
    INDEX
    Explanations

    exclamations and sounds

    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_10/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
     to
    -2.00
    渽
    -1.77
    ,”
    -1.75
    .”
    -1.63
    vignon
    -1.60
    ?
    -1.60
    In
    -1.59
    當初
    -1.59
    但是在
    -1.58
    ”
    -1.58
    POSITIVE LOGITS
     такие
    1.77
    
    1.77
     fraught
    1.62
    сколько
    1.60
    栳
    1.55
    </h2>
    1.53
     comenzado
    1.52
    *}\
    1.52
    ticion
    1.52
     descubierto
    1.52
    Activations Density 0.007%

    No Known Activations