© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71595
    Prev
    Next
    INDEX
    Explanations

    future events and actions

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

    The neuron is detecting future‐tense constructions, especially the auxiliary “will” (and related markers indicating something is about to happen).

    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
     sometimes
    -1.13
     could
    -1.12
    覓
    -1.04
     that
    -1.02
     where
    -1.00
     maybe
    -0.96
     perhaps
    -0.95
     growing
    -0.94
     when
    -0.93
    //**
    -0.92
    POSITIVE LOGITS
    hopefully
    1.41
     be
    1.29
    Hopefully
    1.13
     prochain
    1.09
    Doesn
    1.09
     aima
    1.05
    doesn
    1.04
     upcoming
    1.02
    isées
    1.02
    Missed
    1.01
    Activations Density 0.086%

    No Known Activations