© 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. 10-GEMMASCOPE-RES-131K
    7. 71532
    Prev
    Next
    INDEX
    Explanations

    only guess, only hope, only assume

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

    The neuron detects the adverb “only” when it appears (often in phrases like “can only…”).

    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
    麈
    -1.90
    鼷
    -1.84
     all
    -1.84
     –
    -1.75
     сыром
    -1.68
    铪
    -1.66
     hundred
    -1.66
     "."
    -1.66
    〠
    -1.62
    過程中
    -1.59
    POSITIVE LOGITS
    呿
    1.86
     تُ
    1.68
    an
    1.68
     communiquez
    1.65
    set
    1.59
     використовувати
    1.54
    thus
    1.53
    Maybe
    1.52
    with
    1.52
    neg
    1.52
    Activations Density 0.005%

    No Known Activations