© 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. 22-GEMMASCOPE-RES-131K
    7. 65061
    Prev
    Next
    INDEX
    Explanations

    explaining or reporting

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

    The neuron fires on numeric tokens and measurements (e.g. digits, decimal numbers, percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    !
    -0.89
    也没有
    -0.85
    کاربرد
    -0.82
    켓
    -0.79
     چیه
    -0.77
    没有任何
    -0.76
    Msgs
    -0.76
     указа
    -0.76
    testens
    -0.76
    to
    -0.75
    POSITIVE LOGITS
     explains
    1.37
     explained
    1.02
     explaining
    1.02
     then
    1.02
     below
    1.00
     here
    0.96
     now
    0.95
     explain
    0.94
    bản
    0.94
     overras
    0.93
    Activations Density 0.031%

    No Known Activations