© 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. 34-GEMMASCOPE-RES-131K
    7. 45342
    Prev
    Next
    INDEX
    Explanations

    coding syntax, numbers, dates

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

    The neuron fires on instances of the literal “0” (zero).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ་
    -0.81
    勢
    -0.79
     detr
    -0.79
     mossy
    -0.77
    มือ
    -0.73
    omalies
    -0.73
     Inflate
    -0.73
     приготування
    -0.71
     fanciful
    -0.71
     лише
    -0.71
    POSITIVE LOGITS
     NaN
    1.41
     Infinity
    1.41
    Infinity
    1.20
    NaN
    1.19
     Nan
    1.09
    Nan
    1.04
    𝔽
    0.97
     milliards
    0.94
    infinity
    0.93
    NAN
    0.91
    Activations Density 0.030%

    No Known Activations