© 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. 14139
    Prev
    Next
    INDEX
    Explanations

    arbitrary / arbitrarily

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

    The neuron fires on occurrences of “arbitrary” (and its variant “arbitrarily”) in the text.

    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
    ar
    -2.34
     ‘’
    -2.25
     \"
    -2.13
     таких
    -1.90
    ть
    -1.82
     ¨
    -1.81
     –
    -1.81
    чка
    -1.80
     blessé
    -1.80
    
    -1.79
    POSITIVE LOGITS
    0
    1.84
    and
    1.75
    为此
    1.71
     you
    1.69
     by
    1.66
    閦
    1.63
     deswegen
    1.62
     profundamente
    1.58
    旄
    1.58
     but
    1.55
    Activations Density 0.007%

    No Known Activations