© 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. 8308
    Prev
    Next
    INDEX
    Explanations

    it's all

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

    The neuron activates whenever it encounters the word “all.”

    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
     of
    -2.00
    If
    -1.70
    我們
    -1.67
    我们
    -1.66
     the
    -1.66
     sommige
    -1.65
     and
    -1.62
    It
    -1.62
    пыта
    -1.57
    nition
    -1.56
    POSITIVE LOGITS
     basically
    1.84
     essentially
    1.72
     intricate
    1.70
     a
    1.70
     poderosa
    1.67
     their
    1.63
    などを
    1.58
     idén
    1.56
     nemlig
    1.55
    着一个
    1.55
    Activations Density 0.004%

    No Known Activations