© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1447
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    This neuron detects standalone numeric tokens (individual digits appearing in tables, dates, identifiers, or other structured numeric sequences).

    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
     again
    -1.41
     that
    -1.38
     JMenuItem
    -1.14
    herself
    -1.13
    previously
    -1.09
    again
    -1.09
    properly
    -1.09
    those
    -1.09
    今度は
    -1.07
     katk
    -1.07
    POSITIVE LOGITS
    0
    1.70
     including
    1.28
     first
    1.28
    1
    1.16
     such
    1.14
     they
    1.09
     which
    1.06
    <0x80>
    1.02
     primeiro
    1.02
     did
    1.01
    Activations Density 0.092%

    No Known Activations