© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41054
    Prev
    Next
    INDEX
    Explanations

    software build versions and numbers

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

    The neuron detects mentions of software build or version identifiers (e.g., the word “build” followed by a number).

    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
    }
    -2.42
    </h3>
    -2.08
    一番
    -1.95
     требует
    -1.86
     способствует
    -1.81
    ist
    -1.80
     gets
    -1.77
     divides
    -1.76
    出了一
    -1.75
     дает
    -1.73
    POSITIVE LOGITS
    ࿆
    2.56
    闞
    2.20
     elegance
    2.19
    唻
    2.11
    𓇼
    2.09
    ꯸
    2.08
    多样
    2.03
     россия
    2.02
    .):
    2.02
    　　*
    1.99
    Activations Density 0.022%

    No Known Activations