© 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. 73713
    Prev
    Next
    INDEX
    Explanations

    education, wisdom, and social questions

    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
     уже
    -1.20
     zul
    -1.12
     violación
    -1.10
    ְר
    -1.10
    ACCIÓN
    -1.09
    
    -1.09
     arme
    -1.06
     també
    -1.04
     również
    -1.02
     enge
    -1.02
    POSITIVE LOGITS
     I
    1.27
     compared
    1.26
    SOUNDBITE
    1.18
     хорошая
    1.16
     others
    1.12
    Compared
    1.09
     scuro
    1.08
     overall
    1.06
    ients
    1.05
     noticeably
    1.03
    Activations Density 0.013%

    No Known Activations