© 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. 111953
    Prev
    Next
    INDEX
    Explanations

    career development project

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

    The neuron fires strongly on “Career” (or “Careers”) section headings and related “career” tokens marking the start of a biography’s career section.

    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
    虓
    -2.44
    泚
    -2.08
     Daß
    -2.05
    ൎ
    -2.05
    뿍
    -1.95
     всѣ
    -1.94
    的吗
    -1.93
     ktorí
    -1.85
    耵
    -1.85
    玧
    -1.84
    POSITIVE LOGITS
    h
    2.44
    )
    2.28
    0
    2.27
    k
    2.22
    of
    2.11
    (
    2.03
    in
    1.96
    and
    1.89
    x
    1.86
    .”
    1.83
    Activations Density 0.038%

    No Known Activations