© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87032
    Prev
    Next
    INDEX
    Explanations

    models (scientific, statistical, computational)

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

    The neuron consistently activates on occurrences of the word “model” (including its variants like “Model” or “models”).

    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
    ции
    -2.97
    }
    -2.89
     unſ
    -2.88
     we
    -2.73
    ского
    -2.61
    "
    -2.56
     "
    -2.55
    潆
    -2.45
    s
    -2.44
    ization
    -2.42
    POSITIVE LOGITS
    You
    3.27
    They
    3.13
    It
    3.02
    ⢪
    2.81
    ICOLON
    2.80
    However
    2.77
    Ikke
    2.70
    la
    2.66
     tyto
    2.64
    ༑
    2.64
    Activations Density 0.049%

    No Known Activations