© 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. 100810
    Prev
    Next
    INDEX
    Explanations

    job is

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

    The neuron strongly activates on the word “job” (especially when it appears as “job is/your job/is now about,” etc.).

    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
    ꪔ
    -1.76
    趼
    -1.73
     columnIndex
    -1.66
     sebagainya
    -1.64
     fortalec
    -1.63
    इटम
    -1.62
     haute
    -1.62
    らし
    -1.59
     馆
    -1.59
     dårlig
    -1.59
    POSITIVE LOGITS
    in
    2.08
    In
    2.05
    o
    1.93
    os
    1.84
    ac
    1.82
    ae
    1.81
    —
    1.72
    0
    1.69
    on
    1.66
    se
    1.66
    Activations Density 0.008%

    No Known Activations