© 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. 68279
    Prev
    Next
    INDEX
    Explanations

    Limerick, code, questions, expressions

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

    The neuron fires on tokens that name or invoke time‐measuring calls (e.g. datetime.now, time.time, System.currentTimeMillis, etc.).

    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
     ihrer
    -0.89
     saat
    -0.85
     luas
    -0.84
    atical
    -0.83
     hırka
    -0.83
     tapi
    -0.82
     kullan
    -0.82
    Ketua
    -0.82
    İL
    -0.82
     squadra
    -0.82
    POSITIVE LOGITS
     siitä
    1.04
    ientôt
    0.88
     kokona
    0.88
     centímetros
    0.86
     zůst
    0.84
    上で
    0.82
     artikke
    0.82
    msubsup
    0.82
    دانشنامهٔ
    0.82
    =$((
    0.82
    Activations Density 0.002%

    No Known Activations