© 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. 90966
    Prev
    Next
    INDEX
    Explanations

    programming language features

    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
     PROCED
    -0.91
     fonctionner
    -0.84
     الشم
    -0.84
     BROS
    -0.84
     setup
    -0.84
     nuoc
    -0.83
    ']>;
    -0.82
    ęb
    -0.81
     toilettes
    -0.81
     conos
    -0.80
    POSITIVE LOGITS
     language
    1.24
     design
    1.20
     diseño
    1.15
     programmer
    1.14
     orth
    1.11
    orth
    1.09
     Orth
    1.07
    Orth
    1.03
     Diseño
    1.00
     facilities
    1.00
    Activations Density 0.151%

    No Known Activations