© 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. 67196
    Prev
    Next
    INDEX
    Explanations

    still

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

    The neuron is a high‐confidence detector for the adverb “still,” i.e. occurrences of the word “still” indicating continuation or concession.

    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
     &
    -2.70
    \
    -2.58
    觏
    -2.55
    ↵↵
    -2.47
    México
    -2.36
    🢐
    -2.30
    쑨
    -2.28
    烀
    -2.27
    枼
    -2.27
     wichtigste
    -2.27
    POSITIVE LOGITS
    that
    3.08
     antwortete
    3.02
     That
    2.98
    線が
    2.89
     It
    2.55
    That
    2.53
     ยัง
    2.52
    とその
    2.50
    '
    2.38
     fragte
    2.36
    Activations Density 0.024%

    No Known Activations