© 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. 34-GEMMASCOPE-RES-131K
    7. 76770
    Prev
    Next
    INDEX
    Explanations

    out of

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

    The neuron fires on occurrences of the “of” in hyphenated “out-of-” expressions (e.g. out-of-memory, out-of-equilibrium, out-of-date).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    结语
    -0.89
     Mã
    -0.88
     out
    -0.84
    Produto
    -0.82
     případě
    -0.78
    ІІ
    -0.78
    出
    -0.77
    чия
    -0.77
     TILE
    -0.76
     Aufenthalts
    -0.75
    POSITIVE LOGITS
     bounds
    1.03
     Bounds
    1.02
     proportion
    1.00
    sync
    0.96
     pocket
    0.96
    bounds
    0.90
    Bounds
    0.84
    ounds
    0.81
     Pocket
    0.81
     sync
    0.81
    Activations Density 0.014%

    No Known Activations