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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85908
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    The neuron primarily fires on decimal points and numeric measurements (i.e. tokens forming numbers with a “.”).

    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
     ± 
    -1.92
    𖣘
    -1.61
     الداخلية
    -1.60
    下巴
    -1.58
                         
    -1.56
     Kuba
    -1.56
     эмоции
    -1.55
    						
    -1.54
    </sub>
    -1.54
                             
    -1.54
    POSITIVE LOGITS
     of
    2.52
     brinda
    1.88
     Genuss
    1.62
     I
    1.59
    '
    1.57
     aiuto
    1.56
     investigation
    1.55
     fakty
    1.44
     OF
    1.41
     pido
    1.38
    Activations Density 0.095%

    No Known Activations