© 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. 73272
    Prev
    Next
    INDEX
    Explanations

    received a scholarship, nomination, letter, email, call

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

    The neuron fires on instances of the indefinite article “a” directly followed by a numerical value, i.e. the pattern “a <number>.”

    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
    go
    -1.81
    (
    -1.77
    infty
    -1.77
    🢒
    -1.73
     godk
    -1.70
    “
    -1.67
    on
    -1.65
    these
    -1.60
    ai
    -1.55
    0
    -1.55
    POSITIVE LOGITS
     time
    1.71
     recientemente
    1.61
    ilität
    1.48
     Einen
    1.47
     هناك
    1.46
     Vielleicht
    1.46
    玟
    1.46
    валі
    1.44
    tora
    1.44
    迄
    1.43
    Activations Density 0.025%

    No Known Activations