© 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. 76215
    Prev
    Next
    INDEX
    Explanations

    document structure and LaTeX

    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
     all
    -0.95
     on
    -0.94
     iso
    -0.92
     less
    -0.85
     intense
    -0.85
     out
    -0.84
     low
    -0.84
     +/-
    -0.82
     non
    -0.82
     not
    -0.81
    POSITIVE LOGITS
     taker
    1.02
     calli
    0.90
     SEVEN
    0.88
    悻
    0.84
     charlotte
    0.84
    ICLES
    0.83
     THIR
    0.83
     NEEDED
    0.82
     viola
    0.82
     WINE
    0.81
    Activations Density 0.000%

    No Known Activations