© 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. 104688
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron fires on numeric tokens (digits, years, counts, measurements, 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
     этого
    -1.05
    ны
    -0.87
    èce
    -0.86
    ナイキ
    -0.86
     этом
    -0.85
     ambiguous
    -0.85
     not
    -0.84
     этому
    -0.83
    ている
    -0.81
    をご紹介します
    -0.81
    POSITIVE LOGITS
     your
    1.12
    ОВО
    1.04
    izzle
    0.98
     wła
    0.96
     my
    0.94
    蟊
    0.93
    those
    0.92
    getSystemService
    0.92
    meist
    0.91
     raconte
    0.91
    Activations Density 0.055%

    No Known Activations