© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14646
    Prev
    Next
    INDEX
    Explanations

    grand things and scale

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

    The neuron fires strongly on occurrences of the adjective “grand” (as in “grand scale,” “grand leap,” “grand reveal,” etc.), i.e. that intensifying descriptor.

    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
     unſ
    -2.95
    赑
    -2.91
    饧
    -2.55
    驺
    -2.44
    ㈰
    -2.39
    푢
    -2.38
    
    -2.34
     ſol
    -2.28
    也会
    -2.28
    哢
    -2.27
    POSITIVE LOGITS
    You
    2.81
    Though
    2.67
    It
    2.67
    Although
    2.63
    Before
    2.63
    While
    2.61
    As
    2.47
    After
    2.45
    Even
    2.45
    All
    2.44
    Activations Density 0.005%

    No Known Activations