© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57601
    Prev
    Next
    INDEX
    Explanations

    most likely or certainly

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

    The neuron consistently spotlights the word "most" when used as an intensifying or superlative modifier.

    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
    maids
    -0.97
    があるので
    -0.95
    ochond
    -0.92
     apartament
    -0.91
    Ѥ
    -0.90
    より
    -0.90
    Tav
    -0.87
     قطاع
    -0.87
     entendre
    -0.87
    το
    -0.87
    POSITIVE LOGITS
     likely
    2.05
     of
    1.81
     certainly
    1.77
     definitely
    1.73
     Definitely
    1.31
     importantly
    1.28
    likely
    1.25
     probably
    1.25
     notably
    1.24
     Certainly
    1.23
    Activations Density 0.029%

    No Known Activations