© 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. 85316
    Prev
    Next
    INDEX
    Explanations

    speaker's future actions

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

    The neuron strongly activates on the word “will,” i.e. instances of the future‐tense auxiliary “will.”

    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
     with
    -2.03
     from
    -1.74
    \
    -1.68
     each
    -1.60
     for
    -1.56
    enada
    -1.55
     oppressive
    -1.53
    ;
    -1.53
     long
    -1.52
    、、
    -1.52
    POSITIVE LOGITS
    鹟
    2.16
    縠
    1.88
     germain
    1.73
    unfortunately
    1.73
     canin
    1.68
     necessari
    1.66
     pernic
    1.66
    currently
    1.62
     infrastruktur
    1.62
     incid
    1.58
    Activations Density 0.029%

    No Known Activations