© 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. 22222
    Prev
    Next
    INDEX
    Explanations

    in the future

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

    The neuron activates on occurrences of the word “future.”

    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
     noemen
    -2.11
    嘮
    -2.03
     reconocida
    -1.82
    銛
    -1.80
    ’:
    -1.80
     in
    -1.80
    kệ
    -1.79
    kijken
    -1.79
     proberen
    -1.77
     шапка
    -1.74
    POSITIVE LOGITS
     '
    2.31
    w
    2.30
    f
    2.30
     we
    2.27
    k
    2.08
    r
    2.03
     will
    1.95
    你的
    1.95
    V
    1.94
    in
    1.91
    Activations Density 0.009%

    No Known Activations