© 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. 59416
    Prev
    Next
    INDEX
    Explanations

    child tax credit

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

    The neuron activates strongly on tokens that are part of named‐entity–style items—especially numbers/dates and capitalized names or places.

    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
     Croft
    -1.12
     podem
    -1.10
    ᚹ
    -1.06
    ⋗
    -1.05
     imponer
    -1.03
    パッド
    -1.02
    "..
    -1.00
    melada
    -0.99
     filozof
    -0.99
    ctibles
    -0.98
    POSITIVE LOGITS
    IN
    1.12
    monės
    1.01
    Then
    0.98
     caval
    0.97
    噴
    0.95
    WHEN
    0.93
    انجليز
    0.93
    ſon
    0.93
    гмент
    0.91
     Ähnliche
    0.91
    Activations Density 0.065%

    No Known Activations