© 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. 31069
    Prev
    Next
    INDEX
    Explanations

    cheap, Hip, Style, Queer, Stuff

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

    The neuron strongly activates on numeric tokens (digit sequences), effectively finding numbers in the text.

    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
    katkan
    -0.84
     Paro
    -0.79
    sividad
    -0.78
     Acquisition
    -0.75
    dangerous
    -0.73
    werd
    -0.73
    offsetWidth
    -0.73
     Guine
    -0.73
     APPELL
    -0.71
     Hodg
    -0.71
    POSITIVE LOGITS
     wholesale
    0.93
     cheap
    0.90
     Subscriptions
    0.82
    cheap
    0.79
    akses
    0.73
    ////
    0.73
     Cheap
    0.71
    assemblée
    0.71
    Fake
    0.70
    replica
    0.69
    Activations Density 0.011%

    No Known Activations