© 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. 19184
    Prev
    Next
    INDEX
    Explanations

    values near 99 percent

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

    The neuron activates on numerical expressions featuring decimals (often representing precise values or percentages).

    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
    -2.22
     Anſ
    -1.64
    
    -1.56
     asamblea
    -1.55
     Públicas
    -1.48
     secoli
    -1.47
    ЛЮ
    -1.45
    fucker
    -1.44
    entious
    -1.44
    慄
    -1.41
    POSITIVE LOGITS
    s
    1.78
    3
    1.76
    2
    1.74
    4
    1.62
    $
    1.55
    n
    1.49
    }
    1.49
     /
    1.49
     crammed
    1.38
    '
    1.37
    Activations Density 0.040%

    No Known Activations