© 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. 10-GEMMASCOPE-RES-131K
    7. 11441
    Prev
    Next
    INDEX
    Explanations

    Tagging and special characters

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

    Font Awesome icon class declarations in HTML/CSS code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     thous
    -1.80
     プル
    -1.48
    several
    -1.45
     walaupun
    -1.44
     fign
    -1.42
     HUND
    -1.42
     williams
    -1.41
     beft
    -1.40
    hundreds
    -1.40
     sayfası
    -1.40
    POSITIVE LOGITS
     of
    1.98
     that
    1.93
     now
    1.57
     auguri
    1.54
     {
    1.46
     упаковка
    1.41
     a
    1.41
    目前
    1.37
     Anliegen
    1.36
     each
    1.35
    Activations Density 0.000%

    No Known Activations