© 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. 41164
    Prev
    Next
    INDEX
    Explanations

    code punctuation and structure

    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
     diferentes
    -1.62
    different
    -1.51
     distintos
    -1.39
     diversos
    -1.35
     différentes
    -1.34
    without
    -1.32
     différents
    -1.30
     cidad
    -1.30
     molti
    -1.30
     múltiples
    -1.28
    POSITIVE LOGITS
     because
    1.58
     during
    1.29
     for
    1.27
     and
    1.27
     regardless
    1.21
    cribes
    1.15
     nestled
    1.14
    突入
    1.13
     it
    1.13
     impressively
    1.13
    Activations Density 0.018%

    No Known Activations