© 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. 28042
    Prev
    Next
    INDEX
    Explanations

    assistant, exec, sub roles

    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
     to
    -1.57
     peuvent
    -1.12
     that
    -1.12
     النظام
    -1.09
    owanym
    -1.08
    类型
    -1.03
    ıç
    -1.02
     cuyo
    -1.00
     pensez
    -0.98
     geschikt
    -0.98
    POSITIVE LOGITS
     aussit
    1.18
    STRUCTIONS
    1.16
    Karakter
    1.16
    Elektron
    1.15
    FORC
    1.12
    帐户
    1.10
     искрен
    1.09
     fidèle
    1.09
     сахара
    1.05
    Дети
    1.05
    Activations Density 0.001%

    No Known Activations