© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102363
    Prev
    Next
    INDEX
    Explanations

    up-and-coming and up and running

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

    The neuron fires on the idiomatic “up and X” constructions—e.g. “up‐and‐coming” or “up and running.”

    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
    ).
    -2.14
    *.
    -2.13
    *,
    -2.06
     I
    -2.02
    {
    -1.98
     }
    -1.82
    </
    -1.80
    \
    -1.80
    }
    -1.74
     lançado
    -1.73
    POSITIVE LOGITS
     ویکی‌پدیا
    2.08
    iencia
    1.87
    луйста
    1.85
    izziness
    1.80
     oreilles
    1.80
    adeira
    1.78
     incapacitated
    1.74
    と感じ
    1.73
     oeufs
    1.72
    嘞
    1.72
    Activations Density 0.005%

    No Known Activations