© 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. 10320
    Prev
    Next
    INDEX
    Explanations

    if-then structure

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

    the word "then" in conditional or logical consequence statements.

    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
     białym
    -1.82
     carrot
    -1.80
     According
    -1.80
     This
    -1.79
    sandalia
    -1.69
    boneca
    -1.63
    指向
    -1.63
     czerwony
    -1.62
     erwähnten
    -1.61
     Vorbereitung
    -1.58
    POSITIVE LOGITS
    '
    2.00
    "
    1.90
     paramInt
    1.73
    }$
    1.71
    ‌‌
    1.70
    _
    1.70
    {
    1.69
     και
    1.68
    *
    1.66
    and
    1.63
    Activations Density 0.007%

    No Known Activations