© 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. 64741
    Prev
    Next
    INDEX
    Explanations

    how many

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

    The neuron fires on phrases and words that express counting or numerical quantity (e.g. “how many,” “times,” “count,” 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
     molto
    -1.08
    iseksi
    -1.00
     când
    -1.00
     вещи
    -0.96
     немного
    -0.96
    itanie
    -0.94
    よろしくお願いします
    -0.94
     is
    -0.93
     другом
    -0.92
     ricardo
    -0.92
    POSITIVE LOGITS
     this
    1.64
     that
    1.27
     each
    1.22
     those
    1.12
     times
    1.09
    canth
    1.07
     actualmente
    1.07
     Lijst
    1.05
     innumerable
    1.02
     poszczegól
    1.02
    Activations Density 0.017%

    No Known Activations