© 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. 77415
    Prev
    Next
    INDEX
    Explanations

    Filipinos and work

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

    The main thing this neuron does is detect numeric tokens (numbers, years, rankings, and other digit 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
    inputValue
    -0.79
    جين
    -0.77
    saco
    -0.75
    incl
    -0.75
     苗
    -0.74
     pozdě
    -0.74
    loadModel
    -0.73
    userLogin
    -0.72
     miteinander
    -0.71
    следования
    -0.71
    POSITIVE LOGITS
    ្
    0.85
    onomie
    0.84
    ophi
    0.83
    ppchen
    0.82
    ニメ
    0.82
     Filipino
    0.80
     Filipinos
    0.80
    či
    0.80
    NFS
    0.79
    образие
    0.77
    Activations Density 0.001%

    No Known Activations