© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119682
    Prev
    Next
    INDEX
    Explanations

    CSS properties like float, position, border, font, background, display, width, margin, padding

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

    indentation or whitespace at the beginning of lines in code, particularly in CSS.

    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
     of
    -2.63
    0
    -1.72
    /
    -1.51
     our
    -1.43
     œufs
    -1.41
    偷偷
    -1.40
     how
    -1.40
     saati
    -1.39
     médec
    -1.38
     him
    -1.36
    POSITIVE LOGITS
     and
    1.77
     encender
    1.75
    申し上げます
    1.55
    unzione
    1.51
     بهذا
    1.50
    เกง
    1.48
    cised
    1.47
    nhold
    1.46
     colorear
    1.45
     ३
    1.38
    Activations Density 0.015%

    No Known Activations