© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113421
    Prev
    Next
    INDEX
    Explanations

    market close

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

    The neuron fires on standalone numeric tokens—especially financial or tabular numbers (prices, percentages, dates) shown in data‐frame or table contexts.

    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
    䜣
    -1.59
     privato
    -1.56
    mmons
    -1.55
    俛
    -1.52
     beiden
    -1.50
    戋
    -1.48
    Eerste
    -1.48
    Daar
    -1.48
     schöne
    -1.45
     quando
    -1.44
    POSITIVE LOGITS
     on
    1.63
    '
    1.61
    )
    1.48
     EVERY
    1.35
    </h2>
    1.20
    .
    1.19
     or
    1.16
         
    1.16
     for
    1.16
    I
    1.16
    Activations Density 0.008%

    No Known Activations