© 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. 22-GEMMASCOPE-RES-131K
    7. 12768
    Prev
    Next
    INDEX
    Explanations

    foreign language symbols

    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
     cowok
    -1.50
     overall
    -1.33
    んでる
    -1.29
     of
    -1.27
     również
    -1.24
    小孩子
    -1.24
    やっぱ
    -1.23
     focuses
    -1.23
     Bildschirm
    -1.19
     renowned
    -1.18
    POSITIVE LOGITS
    ₩
    1.53
    ÈNE
    1.45
     thermique
    1.30
     esferas
    1.29
     divertida
    1.27
    Obrigada
    1.24
     disconcer
    1.23
    证书
    1.21
     duas
    1.20
     memastikan
    1.20
    Activations Density 0.063%

    No Known Activations