© 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. 10-GEMMASCOPE-RES-131K
    7. 1100
    Prev
    Next
    INDEX
    Explanations

    research benefits and findings

    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_10/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
     one
    -1.51
    🤠
    -1.25
    👊
    -1.21
    🤑
    -1.20
    😛
    -1.19
    😱
    -1.15
     at
    -1.15
     minuter
    -1.15
     by
    -1.14
     formule
    -1.14
    POSITIVE LOGITS
     tiende
    1.51
     vários
    1.36
    actually
    1.35
     Schluß
    1.31
     incluso
    1.30
     ungewöhn
    1.30
     thậm
    1.29
     ciertas
    1.28
     sogar
    1.27
     ciertos
    1.26
    Activations Density 0.387%

    No Known Activations