© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81054
    Prev
    Next
    INDEX
    Explanations

    user file paths

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

    This neuron primarily activates on multi-digit numeric tokens (i.e. integer numbers).

    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
    itié
    -0.75
     passione
    -0.69
    odos
    -0.68
    illez
    -0.68
     genotyping
    -0.67
    鐢
    -0.67
     پست
    -0.67
    pée
    -0.66
     APPLIC
    -0.66
     réservation
    -0.65
    POSITIVE LOGITS
     đến
    0.71
     Tivoli
    0.70
     Revi
    0.69
    irai
    0.68
    responseType
    0.68
    Visa
    0.67
     windscreen
    0.66
    演示
    0.66
     specular
    0.66
     Elo
    0.65
    Activations Density 0.051%

    No Known Activations