© 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. 10-GEMMASCOPE-RES-131K
    7. 111685
    Prev
    Next
    INDEX
    Explanations

    idea of

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

    This neuron detects occurrences of the phrase “the idea of.”

    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
     those
    -1.95
     embarazada
    -1.88
    哢
    -1.69
     comprando
    -1.63
     these
    -1.58
     grossa
    -1.58
     cuando
    -1.45
     केवल
    -1.45
     slechts
    -1.41
     luchar
    -1.41
    POSITIVE LOGITS
    ⇹
    1.71
    𓍊
    1.70
    eterminate
    1.68
     自己
    1.64
     marquées
    1.56
    ፑ
    1.54
    f
    1.53
     вариан
    1.52
     (
    1.52
    ícios
    1.51
    Activations Density 0.006%

    No Known Activations