© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13326
    Prev
    Next
    INDEX
    Explanations

    other noun

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

    The neuron activates on words meaning “other” or “remaining” (e.g. Russian «другие», «других», «остальные»).

    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
            
    -2.97
    *
    -2.81
     
    -2.81
    -
    -2.78
    <
    -2.66
     l
    -2.53
    1
    -2.31
      
    -2.31
     be
    -2.27
     *
    -2.25
    POSITIVE LOGITS
    følgelig
    3.06
    瀦
    3.05
    ꦠ
    3.00
    羂
    2.84
    杙
    2.83
    worldly
    2.80
    蓥
    2.77
     शुर
    2.69
    .《
    2.63
     godk
    2.63
    Activations Density 0.001%

    No Known Activations