© 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. 93281
    Prev
    Next
    INDEX
    Explanations

    University Inc. fellowship scholarship

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

    The neuron fires on uppercase‐style tokens—acronyms, organization names, and monetary or funding‐related terms (e.g. “FTE,” “Inc,” “US,” “Fund,” “ten,” “dollar”).

    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
    ｀*)
    -0.79
    featureID
    -0.73
     localization
    -0.73
     deportation
    -0.72
     enf
    -0.69
     découvre
    -0.69
    王者
    -0.69
    nė
    -0.68
     ruins
    -0.68
    itle
    -0.68
    POSITIVE LOGITS
     Fulbright
    0.95
    Ful
    0.81
     correl
    0.74
     getS
    0.73
    óngase
    0.72
    Scholar
    0.72
     competente
    0.69
     ETA
    0.69
     advising
    0.69
    uku
    0.68
    Activations Density 0.018%

    No Known Activations