© 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. 120055
    Prev
    Next
    INDEX
    Explanations

    names like Kathryn, Pablo, Tara

    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
    derdag
    -2.80
    ?"
    -2.63
    !'
    -2.61
    一亮
    -2.55
    呖
    -2.50
    隄
    -2.41
     Jednak
    -2.39
    誂
    -2.38
    ко
    -2.36
    蹿
    -2.36
    POSITIVE LOGITS
     he
    2.67
    ーーー
    2.66
    1
    2.64
    {
    2.56
    </td>
    2.28
     technischen
    2.20
    Will
    2.20
    はじめ
    2.17
    她就
    2.17
     Bildern
    2.16
    Activations Density 0.002%

    No Known Activations