© 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. 79945
    Prev
    Next
    INDEX
    Explanations

    current state or time

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

    The neuron flags multi‐word nominal compounds that describe specific features, states, or shifts.

    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
    形で
    -0.77
    力で
    -0.77
     वर्
    -0.73
    を行い
    -0.73
    Expiry
    -0.73
     If
    -0.72
     is
    -0.72
     già
    -0.71
    Nomenclature
    -0.71
    istor
    -0.71
    POSITIVE LOGITS
     now
    2.58
     anymore
    2.36
     artık
    2.23
     теперь
    2.16
     अब
    1.98
    不再
    1.95
     ahora
    1.92
    Теперь
    1.79
     désormais
    1.71
    now
    1.54
    Activations Density 0.070%

    No Known Activations