© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69396
    Prev
    Next
    INDEX
    Explanations

    Salutations and codes

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

    The neuron is strongly activated by numeric literals (numbers or numeric substrings, including integers and decimals).

    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
    ↵
    -3.89
    ↵↵
    -2.59
    la
    -2.31
    </strong>
    -2.22
     We
    -2.14
    .”
    -1.95
    各样的
    -1.93
    li
    -1.91
    }(
    -1.91
     Take
    -1.89
    POSITIVE LOGITS
     épreuve
    2.47
    쫀
    2.31
    킁
    2.30
     we
    2.22
    橚
    2.22
    ਊ
    2.20
    怏
    2.14
    would
    2.11
    
    2.09
    変わらず
    2.08
    Activations Density 0.001%

    No Known Activations