© 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. 22-GEMMASCOPE-RES-131K
    4. 73909
    Prev
    Next
    INDEX
    Explanations

    android code examples

    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_22/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
     plafon
    -1.23
     vírus
    -1.20
     tragé
    -1.15
    weitere
    -1.14
     fré
    -1.12
    罍
    -1.12
     verzi
    -1.07
     fiscales
    -1.07
     kabát
    -1.06
     triko
    -1.04
    POSITIVE LOGITS
     —
    1.15
    ैंड
    0.98
     altında
    0.94
     And
    0.93
    そうです
    0.93
     recibirá
    0.91
    悅
    0.90
     kontakta
    0.89
     օ
    0.88
     ultrason
    0.87
    Activations Density 0.025%

    No Known Activations