© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39955
    Prev
    Next
    INDEX
    Explanations

    programming language keywords

    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
     kimi
    -2.00
     klubben
    -1.91
     kader
    -1.91
     butik
    -1.88
     Kristus
    -1.88
     tabak
    -1.87
     kedi
    -1.87
     kado
    -1.85
     kapak
    -1.84
     Consiglio
    -1.83
    POSITIVE LOGITS
     now
    2.11
     a
    1.92
     to
    1.91
     on
    1.90
     will
    1.88
     made
    1.83
     more
    1.83
     created
    1.81
     used
    1.81
     also
    1.81
    Activations Density 0.033%

    No Known Activations