© 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. 74182
    Prev
    Next
    INDEX
    Explanations

    bolded text

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

    The neuron fires on HTML opening bold tags (i.e. “<b>”).

    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
     have
    -2.08
     Then
    -2.00
     To
    -2.00
     Such
    -1.99
     That
    -1.99
     so
    -1.98
     Since
    -1.95
     When
    -1.88
     this
    -1.76
     During
    -1.72
    POSITIVE LOGITS
    mability
    2.23
    鴴
    2.06
    亖
    1.98
    现在
    1.93
    ౧
    1.90
    genodigd
    1.85
    遹
    1.82
    ついに
    1.73
    titial
    1.73
     ""],
    1.73
    Activations Density 0.000%

    No Known Activations