© 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. 33553
    Prev
    Next
    INDEX
    Explanations

    today's activities and updates

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

    The neuron is primarily detecting numeric expressions (digits, dates, counts, percentages, 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_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
    YEAR
    -0.94
    gående
    -0.93
     año
    -0.91
     сначала
    -0.88
    Years
    -0.81
    ปี
    -0.80
    onoi
    -0.80
    ❓
    -0.79
    refreshToken
    -0.79
     ahí
    -0.79
    POSITIVE LOGITS
     again
    1.80
     continuing
    1.64
     continue
    1.59
     очеред
    1.59
     continues
    1.52
     today
    1.48
    再次
    1.45
     updates
    1.45
     latest
    1.41
     erneut
    1.39
    Activations Density 0.088%

    No Known Activations