© 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. 74998
    Prev
    Next
    INDEX
    Explanations

    company types

    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
    al
    -1.95
    p
    -1.86
    </h2>
    -1.80
    c
    -1.70
    ter
    -1.69
    os
    -1.68
    u
    -1.66
    j
    -1.66
     less
    -1.61
    Despite
    -1.59
    POSITIVE LOGITS
     créer
    1.68
    傒
    1.67
     menant
    1.63
    珦
    1.61
     konflikt
    1.57
    ТЕЛЬ
    1.56
     帅气
    1.56
    tku
    1.56
    鼋
    1.56
     aktual
    1.55
    Activations Density 0.665%

    No Known Activations