© 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. 10-GEMMASCOPE-RES-131K
    7. 10853
    Prev
    Next
    INDEX
    Explanations

    Ph.D. titles

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

    The neuron is looking for mentions of the academic degree “Ph.D.” (and related degree tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    งิน
    -2.48
     are
    -2.44
    骉
    -2.30
    岀
    -2.25
    铊
    -2.19
     luxuri
    -2.17
    憷
    -2.14
    蟜
    -2.14
     conster
    -2.14
     [];
    -2.14
    POSITIVE LOGITS
    From
    2.53
    0
    2.47
    .
    2.42
    In
    2.39
    ではでは
    2.22
    *
    2.14
    from
    2.09
    s
    2.06
    ではまた
    2.05
    Four
    1.94
    Activations Density 0.006%

    No Known Activations