© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32609
    Prev
    Next
    INDEX
    Explanations

    where followed by things or services

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

    The neuron fires on semantically salient content words—especially title or heading terms and other prominent nouns—highlighting key topic words in the 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
     folklor
    -0.86
     chaussure
    -0.82
    หร
    -0.81
     Herren
    -0.80
    璣
    -0.79
    واد
    -0.79
    ?=
    -0.79
     cheering
    -0.78
    ∊
    -0.77
    ктор
    -0.77
    POSITIVE LOGITS
    वाह
    0.80
    ナルド
    0.79
    tachten
    0.77
     получил
    0.76
     productie
    0.75
     эпи
    0.74
    endu
    0.72
     соста
    0.72
    bibitem
    0.72
     yow
    0.71
    Activations Density 0.013%

    No Known Activations