© 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. 22-GEMMASCOPE-RES-131K
    4. 68388
    Prev
    Next
    INDEX
    Explanations

    mathematical and data processing concepts

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

    The neuron detects mentions of computing the probability of occurrence (e.g. “calculates the probability of [each/pattern] occurrence”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    aterally
    -1.45
     السياس
    -1.41
    Meine
    -1.38
    newblock
    -1.38
    cipes
    -1.38
    Leider
    -1.35
     Dennoch
    -1.34
     Gleichzeitig
    -1.34
    Zwei
    -1.32
     Insgesamt
    -1.32
    POSITIVE LOGITS
     épices
    1.34
     céramique
    1.30
    كوين
    1.27
     godz
    1.24
    underset
    1.19
     кроссовки
    1.14
    🧪
    1.13
     suéter
    1.12
     иннова
    1.12
    اصله
    1.12
    Activations Density 0.022%

    No Known Activations