© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45241
    Prev
    Next
    INDEX
    Explanations

    end of sentence punctuation

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

    This neuron fires on boilerplate site‐interface elements—things like brackets or parentheses and “click here”/sign-up call-to-action links—rather than on the main article text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    toDouble
    -1.04
     arany
    -1.03
     Duits
    -1.01
    izowane
    -1.01
     كرة
    -1.00
     Söz
    -0.99
     collègues
    -0.97
     Dokter
    -0.96
     televisiva
    -0.94
    arrón
    -0.94
    POSITIVE LOGITS
     and
    1.30
     এবং
    1.13
    或者
    1.13
    并且
    1.02
    或
    1.01
     şeyi
    0.98
    หรือ
    0.96
     hoặc
    0.96
    <h3>
    0.95
     Glaubens
    0.94
    Activations Density 0.130%

    No Known Activations