© 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. 63349
    Prev
    Next
    INDEX
    Explanations

    return URLs or actions

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

    The neuron fires on numeric tokens (sequences of digits such as version numbers, port numbers, IDs, etc.).

    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
    química
    -0.79
    haustible
    -0.78
     Chet
    -0.73
     Sarkar
    -0.72
    edrez
    -0.72
     تازه
    -0.69
    baris
    -0.69
    cão
    -0.68
    vál
    -0.67
    枷
    -0.67
    POSITIVE LOGITS
     return
    3.89
    Return
    3.05
     Return
    3.00
    return
    2.55
     RETURN
    2.28
    RETURN
    2.23
     returning
    1.77
     retur
    1.74
     returns
    1.70
     retorno
    1.69
    Activations Density 0.048%

    No Known Activations