© 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. 22-GEMMASCOPE-RES-131K
    7. 16320
    Prev
    Next
    INDEX
    Explanations

    past tense statements

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

    The neuron strongly activates on past‐tense “to be” or “to have” openings—especially clauses beginning with “It was…” or “It had….”

    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
    -1.63
     currently
    -1.45
    currently
    -1.42
    Currently
    -1.25
     you
    -1.19
    your
    -1.09
     derzeit
    -1.05
     RouterModule
    -1.02
    目前
    -1.02
     is
    -1.00
    POSITIVE LOGITS
     wasn
    1.95
     was
    1.48
     didn
    1.44
     ήταν
    1.34
     later
    1.28
     yesterday
    1.28
     originally
    1.27
     afterwards
    1.25
     volna
    1.23
     weren
    1.20
    Activations Density 0.042%

    No Known Activations