© 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. 34683
    Prev
    Next
    INDEX
    Explanations

    title, ACTION, /*, Nucle, DO, Does

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

    The neuron strongly fires on numeric tokens (e.g. version numbers, counts, or other standalone digits).

    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
    Răsp
    -0.89
     gæ
    -0.85
     revital
    -0.82
    滚动
    -0.82
    jeuner
    -0.82
     bera
    -0.81
    SCSI
    -0.81
     procrastin
    -0.80
    锗
    -0.79
     on
    -0.79
    POSITIVE LOGITS
     sentence
    1.44
     beantragt
    1.23
     word
    1.23
     sentences
    1.19
    sentence
    1.17
     words
    1.03
     gefördert
    1.02
    Word
    0.97
     anzunehmen
    0.97
    WORD
    0.96
    Activations Density 0.001%

    No Known Activations