© 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. 44250
    Prev
    Next
    INDEX
    Explanations

    presenting or currently existing

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

    The neuron fires whenever it sees the token “present.”

    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
     Dinas
    -2.44
     quintessential
    -2.44
    the
    -2.39
     três
    -2.36
     \
    -2.36
     dwóch
    -2.34
     overarching
    -2.28
     ใน
    -2.27
    かわい
    -2.17
     cinco
    -2.13
    POSITIVE LOGITS
    There
    2.28
    It
    2.28
    !!!!!
    2.16
     went
    2.16
     seemed
    2.08
    يته
    2.08
     Though
    2.03
    蕯
    2.03
     began
    2.03
     There
    2.03
    Activations Density 0.030%

    No Known Activations