© 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. 10-GEMMASCOPE-RES-131K
    4. 80625
    Prev
    Next
    INDEX
    Explanations

    time passing, past, ages, forever

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

    The neuron activates on multiword expressions that convey a long passage of time (e.g. “what seems like forever,” “ages ago,” “a long time ago”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     всі
    -1.45
     größe
    -1.44
    doppel
    -1.38
     CALIFOR
    -1.36
     historii
    -1.34
     lasciare
    -1.30
     kategorii
    -1.30
    懟
    -1.30
     automóviles
    -1.30
     notare
    -1.30
    POSITIVE LOGITS
     "..\..\..\
    1.41
    It
    1.36
    ti
    1.30
    )\}
    1.30
     ago
    1.27
     hayal
    1.27
    Ста
    1.23
    «
    1.21
    ابراین
    1.20
    enosine
    1.19
    Activations Density 0.065%

    No Known Activations