© 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. 10-GEMMASCOPE-RES-131K
    7. 43980
    Prev
    Next
    INDEX
    Explanations

    work closely with

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

    The neuron fires on the word “closely” (often in the phrase “closely with”), i.e. expressions of close collaboration or working together.

    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
    KommentareTeilen
    -1.61
    侮
    -1.47
    mıştır
    -1.47
    柘
    -1.46
     casada
    -1.45
    曲は
    -1.45
    xnn
    -1.42
    彼女は
    -1.42
    aktif
    -1.41
     hacemos
    -1.40
    POSITIVE LOGITS
    f
    1.83
    v
    1.75
    urs
    1.72
    us
    1.70
    x
    1.67
    to
    1.63
    うーん
    1.61
    鞴
    1.60
     Inſ
    1.57
    鮡
    1.55
    Activations Density 0.005%

    No Known Activations