© 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. 22
    Prev
    Next
    INDEX
    Explanations

    achievements and rankings

    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
     comprenant
    -1.20
    verarbeitung
    -1.18
    lld
    -1.07
     goc
    -1.05
    pte
    -1.03
    art
    -1.02
    굼
    -1.02
     supérieure
    -1.01
     thuy
    -1.00
     lud
    -1.00
    POSITIVE LOGITS
     in
    1.85
    Shortly
    1.34
    There
    1.26
    Unlike
    1.23
    Interestingly
    1.20
    While
    1.18
     within
    1.16
     just
    1.15
    Ironically
    1.12
    Surprisingly
    1.11
    Activations Density 0.056%

    No Known Activations