© 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. 71636
    Prev
    Next
    INDEX
    Explanations

    numbers, specific words, followed by punctuation

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

    The neuron fires strongly on tokens found in official announcement headlines—especially date numbers, exam identifiers, and answer‐key release notices.

    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
     “
    -1.69
     chré
    -1.65
     nuestra
    -1.61
    jący
    -1.59
     I
    -1.59
     fronteras
    -1.57
     problemas
    -1.52
     lámparas
    -1.50
     ἡ
    -1.49
     nuestro
    -1.48
    POSITIVE LOGITS
     to
    2.00
    ֶּ
    1.71
    ּוֹ
    1.70
    giày
    1.41
    のね
    1.35
     possano
    1.34
     poë
    1.34
     fornire
    1.34
    ֵּ
    1.33
     médicaux
    1.33
    Activations Density 0.040%

    No Known Activations