© 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. 30968
    Prev
    Next
    INDEX
    Explanations

    email addresses and domain names

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

    The neuron fires on code tokens specifying the CharSet argument in a DllImport attribute (e.g. “CharSet=Unicode”).

    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
    惬
    -0.66
    Lynn
    -0.64
     Bef
    -0.63
     Feld
    -0.63
    rior
    -0.62
     Nor
    -0.61
     survivor
    -0.61
    рта
    -0.60
    ETA
    -0.60
    LEBR
    -0.60
    POSITIVE LOGITS
     Fland
    0.73
     Stormwater
    0.71
    reversed
    0.70
    stacles
    0.70
    둔
    0.69
    GO
    0.68
    itemID
    0.67
    Quin
    0.67
    enddo
    0.66
    𝒞
    0.66
    Activations Density 0.057%

    No Known Activations