© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43626
    Prev
    Next
    INDEX
    Explanations

    start of a summary

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

    The neuron strongly activates on numeric tokens or number‐like sequences (e.g. “194,” “65,” “8/100,” version numbers, scores, etc.).

    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
    );
    
    -1.82
    %;
    
    -1.75
    ')):
    -1.67
     taką
    -1.66
     ſaid
    -1.63
    ()?;
    -1.62
     Перейти
    -1.57
     FontWeight
    -1.52
    approximately
    -1.50
     NEW
    -1.48
    POSITIVE LOGITS
     that
    2.28
     while
    1.82
     during
    1.78
     but
    1.76
     phenomenal
    1.70
    </h2>
    1.67
     immensely
    1.66
     would
    1.63
    蓓
    1.59
     suoi
    1.59
    Activations Density 0.045%

    No Known Activations