© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 68288
    Prev
    Next
    INDEX
    Explanations

    long term processes

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

    The neuron strongly activates on words and phrases that refer to time passing or long‐duration processes (e.g. “takes time,” “programmes take a long time,” “month,” “process,” “patience”).

    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
     wagen
    -0.96
     peintures
    -0.88
    lieving
    -0.87
     sentral
    -0.87
    cribing
    -0.87
    次に
    -0.85
    ędz
    -0.84
     участи
    -0.84
     maand
    -0.83
     UserModel
    -0.83
    POSITIVE LOGITS
     patience
    1.64
     time
    1.49
    Patience
    1.38
     long
    1.34
     slower
    1.27
     Patience
    1.24
     until
    1.18
     Geduld
    1.17
     gradual
    1.17
     months
    1.17
    Activations Density 0.014%

    No Known Activations