© 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. 36584
    Prev
    Next
    INDEX
    Explanations

    activities before or during eventsor actions

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

    The neuron is tuned to pick out past‐tense verbs (especially reporting verbs like “introduced,” “found,” “asked,” etc.).

    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
    沵
    -1.27
    饸
    -1.27
    PENDAHULUAN
    -1.27
     dégust
    -1.24
    perhaps
    -1.23
     célè
    -1.22
    ほんとに
    -1.21
    ほんと
    -1.20
     Nigeria
    -1.20
     suatu
    -1.20
    POSITIVE LOGITS
     during
    1.30
     but
    1.23
     including
    1.22
    bicara
    1.20
     at
    1.09
    ː
    1.03
     before
    1.03
     people
    1.02
     explicar
    1.02
     increase
    1.02
    Activations Density 0.000%

    No Known Activations