© 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. 79995
    Prev
    Next
    INDEX
    Explanations

    names like Pao Yang, Yongxuan Su

    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
    為に
    -1.47
    奬
    -1.33
     and
    -1.21
    事です
    -1.20
    のお話
    -1.16
    ductory
    -1.10
     neither
    -1.10
    ないです
    -1.06
    のでしょう
    -1.05
     like
    -1.04
    POSITIVE LOGITS
     fiabilité
    1.38
    ECTOS
    1.27
     мальчика
    1.25
    などが
    1.25
     åren
    1.23
     """",
    1.22
     espectacular
    1.20
    zegorz
    1.20
     novamente
    1.20
     considérons
    1.20
    Activations Density 0.020%

    No Known Activations