© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58695
    Prev
    Next
    INDEX
    Explanations

    to followed by determiner/noun

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

    The neuron fires on tokens that are numeric values (integers or decimals).

    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
    .
    -2.89
     οποία
    -2.08
     You
    -2.08
    是他
    -2.05
      
    -2.03
    <bos>
    -2.02
     
    -1.86
     A
    -1.80
    []
    -1.79
    ве
    -1.78
    POSITIVE LOGITS
     our
    2.72
     the
    2.66
    ቍ
    2.16
     these
    2.13
     that
    2.11
     a
    2.08
     télécommande
    2.02
     any
    1.97
    蹩
    1.96
     it
    1.95
    Activations Density 0.702%

    No Known Activations