© 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. 67651
    Prev
    Next
    INDEX
    Explanations

    specific examples after certain

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

    This neuron fires on occurrences of the word “certain” (i.e. the determiner/quantifier “certain”).

    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
    )
    -2.16
    鼕
    -1.83
    橚
    -1.82
    şk
    -1.78
     avions
    -1.76
    ТР
    -1.70
     zoude
    -1.66
    棡
    -1.66
    鶫
    -1.66
     ezt
    -1.66
    POSITIVE LOGITS
    辚
    2.16
     aspects
    2.14
     various
    1.98
    形で
    1.82
     types
    1.80
    瞜
    1.79
     grouped
    1.77
    urlpatterns
    1.71
     furthering
    1.69
    Making
    1.65
    Activations Density 0.020%

    No Known Activations