© 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. 22-GEMMASCOPE-RES-131K
    7. 26997
    Prev
    Next
    INDEX
    Explanations

    future possibilities

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

    This neuron fires on words and phrases expressing future intentions, plans, or desires (e.g., “hoping,” “going to,” “try,” “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_22/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
     your
    -1.40
     snabbt
    -1.15
     다른
    -1.11
     you
    -1.00
     altre
    -1.00
    しなかった
    -1.00
    不夠
    -0.99
    当時は
    -0.97
     rapidamente
    -0.96
    itian
    -0.96
    POSITIVE LOGITS
     someday
    2.05
    Someday
    1.46
     Когда
    1.20
    When
    1.17
    Whenever
    1.17
     vuonna
    1.13
    Hopefully
    1.09
    可能
    1.09
     kiedyś
    1.09
    when
    1.08
    Activations Density 0.012%

    No Known Activations