© 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. 62873
    Prev
    Next
    INDEX
    Explanations

    there is/are/was/were

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

    The neuron detects multi-digit numeric tokens—especially four-digit numbers such as years or similar large numeric codes.

    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
     خدم
    -1.00
    ndo
    -0.93
     acolo
    -0.91
    conia
    -0.90
    rieta
    -0.88
     sebag
    -0.86
    mbda
    -0.86
     allí
    -0.85
    ρού
    -0.84
     نان
    -0.84
    POSITIVE LOGITS
     can
    1.70
     exist
    1.54
     exists
    1.48
     occur
    1.37
     occurs
    1.27
     existed
    1.27
     emerge
    1.26
     is
    1.24
     emerged
    1.20
     comes
    1.19
    Activations Density 0.044%

    No Known Activations