© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129919
    Prev
    Next
    INDEX
    Explanations

    programming code and technical terms

    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
     their
    -1.45
     ardından
    -1.42
    ně
    -1.35
    
    -1.34
     oasis
    -1.34
     ktorí
    -1.33
    葙
    -1.30
    
    -1.30
     ktorá
    -1.30
    blech
    -1.30
    POSITIVE LOGITS
     like
    1.55
     such
    1.44
     with
    1.36
    んですか
    1.30
    ねば
    1.28
    like
    1.27
     you
    1.24
     editados
    1.21
    oznam
    1.20
    Like
    1.19
    Activations Density 0.008%

    No Known Activations