© 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. 105264
    Prev
    Next
    INDEX
    Explanations

    asserting checks

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

    assertion and checking function calls in test code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires on assertion or test-verification keywords (e.g. “assert”, “check”, “CHECK”) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     but
    -1.59
    KommentareTeilen
    -1.55
    
    -1.48
    を持っている
    -1.47
    ]^{-
    -1.42
    ipzig
    -1.41
     to
    -1.41
     Umständen
    -1.37
    ጧ
    -1.37
     خدمة
    -1.35
    POSITIVE LOGITS
    最初に
    1.52
     Sehingga
    1.37
    iriman
    1.36
     eşofman
    1.36
     Misalnya
    1.31
     Dzięki
    1.30
     ahol
    1.28
    erializer
    1.27
     that
    1.27
     like
    1.25
    Activations Density 0.006%

    No Known Activations