© 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. 34-GEMMASCOPE-RES-131K
    7. 47553
    Prev
    Next
    INDEX
    Explanations

    list item or number separators

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

    The neuron activates on numeric tokens—especially multi‐digit numbers such as years, timestamps, and other large numerals.

    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
    -0.77
    \}$
    -0.76
    demie
    -0.73
    . 
    -0.73
     selber
    -0.73
     querían
    -0.71
     hubiese
    -0.70
    vei
    -0.69
    kelig
    -0.69
    }}=$
    -0.69
    POSITIVE LOGITS
     ,
    3.58
     ,
    2.39
     ，
    1.98
     ,\
    1.98
     ,"
    1.98
     ،
    1.91
     ,,
    1.60
     ,'
    1.60
     .,
    1.53
     ;
    1.43
    Activations Density 0.277%

    No Known Activations