© 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. 34-GEMMASCOPE-RES-131K
    7. 2416
    Prev
    Next
    INDEX
    Explanations

    issues and characteristics

    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_34/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
    st
    -1.12
    ⏜
    -1.08
    arised
    -1.08
    ѳ
    -1.08
     Firstly
    -1.05
    ESSO
    -1.05
    🙎
    -1.05
     mense
    -1.04
    ieten
    -1.03
     incentiv
    -1.02
    POSITIVE LOGITS
     presumably
    1.21
     monies
    1.19
     relatively
    1.11
     Getränke
    1.10
     virtually
    1.09
     persons
    1.09
     seemed
    1.08
     indicated
    1.07
     considerably
    1.06
     العديد
    1.06
    Activations Density 0.341%

    No Known Activations