© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1628
    Prev
    Next
    INDEX
    Explanations

    code comments

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

    The neuron is primarily fire­ing on numeric tokens, i.e. counts or numbers 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
    Pert
    -0.79
     Pert
    -0.73
    western
    -0.71
    Away
    -0.71
    scanner
    -0.71
     Bird
    -0.68
    AWAY
    -0.67
    zło
    -0.66
    觉得自己
    -0.66
     liegt
    -0.66
    POSITIVE LOGITS
     Sapi
    0.69
    omial
    0.68
     hold
    0.66
    ftime
    0.66
     Priory
    0.65
    tettu
    0.65
     Cipri
    0.65
    蛎
    0.65
     Exor
    0.65
    ⼤
    0.64
    Activations Density 0.048%

    No Known Activations