© 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. 109453
    Prev
    Next
    INDEX
    Explanations

    code structure and separators

    np_acts-logits-general · gemini-2.5-flash-lite

    the presence of numeric literals (tokens consisting of digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     took
    -0.88
    衞
    -0.85
    веси
    -0.85
     give
    -0.82
     during
    -0.81
     several
    -0.81
     $(
    -0.80
     most
    -0.80
     has
    -0.79
     does
    -0.78
    POSITIVE LOGITS
     ytter
    0.91
     geene
    0.90
     recente
    0.88
     luscious
    0.87
     STYLE
    0.87
     manier
    0.86
     SING
    0.86
    essed
    0.85
    ︲
    0.82
     chè
    0.82
    Activations Density 0.001%

    No Known Activations