© 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. 34-GEMMASCOPE-RES-131K
    4. 116771
    Prev
    Next
    INDEX
    Explanations

    default constructor

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

    The neuron is picking out numeric literals (sequences of digits) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     安装
    -0.93
     ayaa
    -0.77
     movilidad
    -0.77
     immédiatement
    -0.77
     dépenses
    -0.75
    Supervision
    -0.75
     undervalued
    -0.75
    ಲ್
    -0.75
     pouvaient
    -0.75
     progressivement
    -0.74
    POSITIVE LOGITS
     default
    2.78
    default
    2.45
     Default
    2.28
    Default
    2.25
     DEFAULT
    1.85
    DEFAULT
    1.80
     defaults
    1.76
    默认
    1.76
     defaulted
    1.63
    isDefault
    1.52
    Activations Density 0.019%

    No Known Activations