© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71219
    Prev
    Next
    INDEX
    Explanations

    words starting with out

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

    The neuron is picking up the verb roots in “out-X” comparison constructions (e.g. outscored, outgunned, outlive, out-selling).

    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
     to
    -2.88
     has
    -1.80
    )
    -1.75
     betyr
    -1.69
     in
    -1.66
    iscono
    -1.63
     since
    -1.59
     },
    -1.59
     appears
    -1.55
    ⇨
    -1.55
    POSITIVE LOGITS
    
    2.22
     çanta
    2.20
    5
    2.19
    亹
    2.02
    颌
    2.02
     baik
    1.99
    奩
    1.98
     yelek
    1.96
     bardak
    1.95
     kollu
    1.92
    Activations Density 0.006%

    No Known Activations