© 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. 119686
    Prev
    Next
    INDEX
    Explanations

    if conditions

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

    the word "If" at the beginning of comments or conditional statements in 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
    觏
    -1.48
    konen
    -1.44
    Jornal
    -1.44
    ŚĆ
    -1.38
    混ぜ
    -1.37
    various
    -1.37
    和他
    -1.37
    cová
    -1.37
    ILL
    -1.36
    copic
    -1.34
    POSITIVE LOGITS
     this
    2.14
     it
    2.03
    If
    1.94
     there
    1.80
     if
    1.80
     where
    1.70
     each
    1.64
     all
    1.64
     were
    1.61
    如果
    1.60
    Activations Density 0.041%

    No Known Activations