© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129045
    Prev
    Next
    INDEX
    Explanations

    linking sequential actions

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

    The neuron is keyed to numeric tokens or quantities (e.g. large numbers or dosage values) in technical 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_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
    
    -1.81
    mentaux
    -1.73
     podían
    -1.66
    崚
    -1.62
    หรือ
    -1.62
    除了
    -1.59
    beispiel
    -1.57
     podía
    -1.56
    虽然
    -1.54
    wości
    -1.53
    POSITIVE LOGITS
    '
    2.14
    "
    2.13
    {
    2.09
    us
    1.70
    }
    1.69
    _
    1.66
    1.66
    のが
    1.57
    ot
    1.52
    /
    1.52
    Activations Density 0.025%

    No Known Activations