© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124614
    Prev
    Next
    INDEX
    Explanations

    separators or delimiters

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

    The neuron detects numeric literal tokens in the input (i.e. standalone number values).

    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
     to
    -4.53
     in
    -3.89
     as
    -3.81
     and
    -3.66
     that
    -3.41
     by
    -3.27
     or
    -3.27
     but
    -2.92
     at
    -2.92
     on
    -2.78
    POSITIVE LOGITS
     soucis
    3.41
     mété
    3.41
    傒
    3.16
     patienter
    3.14
     enthou
    3.09
    饜
    3.06
     cinto
    3.02
     diki
    3.02
     véritables
    3.00
     diriger
    2.98
    Activations Density 0.314%

    No Known Activations