© 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. 10-GEMMASCOPE-RES-131K
    7. 99689
    Prev
    Next
    INDEX
    Explanations

    time in seconds

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

    The neuron detects numeric time‐interval expressions in seconds (e.g. “5 seconds,” “1 second,” “0.5 hrs”).

    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
    烝
    -1.75
    媜
    -1.70
     messaggio
    -1.69
    にい
    -1.69
     progetto
    -1.66
    ¹.
    -1.66
    …’
    -1.63
    ….”
    -1.63
    何时
    -1.61
     haupts
    -1.59
    POSITIVE LOGITS
     '
    2.42
    that
    2.09
    "
    2.08
    ,"
    2.06
     "
    2.03
    ll
    1.88
     (
    1.75
     â
    1.74
    ]
    1.70
     đó
    1.68
    Activations Density 0.015%

    No Known Activations