© 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. 70297
    Prev
    Next
    INDEX
    Explanations

    twenty and a number

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

    The neuron specifically detects the spelled-out word “twenty” (as part of cardinal numbers like “twenty-four,” “twenty-nine,” etc.).

    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
     pueden
    -2.78
    更好
    -2.73
     weichen
    -2.63
    籏
    -2.61
     possono
    -2.55
    ?’
    -2.55
     encontram
    -2.52
     schicken
    -2.48
    跄
    -2.47
     angep
    -2.45
    POSITIVE LOGITS
    In
    2.97
    This
    2.97
     It
    2.94
    If
    2.86
    喲
    2.80
    When
    2.73
     With
    2.67
     That
    2.63
    ].
    2.56
    ｹ
    2.50
    Activations Density 0.005%

    No Known Activations