© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38512
    Prev
    Next
    INDEX
    Explanations

    dates and timestamps

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

    The neuron strongly activates on numeric tokens containing colons—i.e. time stamps or diff‐header time codes.

    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
     kupić
    -0.94
    råd
    -0.93
    ᾰ
    -0.88
    ){$\
    -0.87
     görüntüleri
    -0.86
     Vergangenheit
    -0.85
    celular
    -0.84
     segni
    -0.84
    的表情
    -0.83
    AtEndOf
    -0.82
    POSITIVE LOGITS
     Infantil
    0.94
     ಇ
    0.93
     útil
    0.93
    zzazione
    0.90
    研究生
    0.90
    通貨
    0.88
    isEmail
    0.87
     න
    0.87
    理工
    0.86
     useful
    0.85
    Activations Density 0.003%

    No Known Activations