© 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. 104623
    Prev
    Next
    INDEX
    Explanations

    watch this or the

    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
    至於
    -1.66
    𖥧
    -1.60
     föres
    -1.60
     participó
    -1.57
     pazi
    -1.57
     ésta
    -1.55
     acidente
    -1.55
     séjours
    -1.55
     invitado
    -1.53
    篥
    -1.53
    POSITIVE LOGITS
     the
    2.23
    我们
    1.75
    ᜀ
    1.74
    </i>
    1.71
     делает
    1.66
     he
    1.62
     которые
    1.61
    
    1.61
     nasze
    1.61
     той
    1.59
    Activations Density 0.011%

    No Known Activations