© 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. 38761
    Prev
    Next
    INDEX
    Explanations

    thanks Invest

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

    This neuron fires strongly on words that begin new lines or blocks—i.e. tokens that serve as section headings or the first word of a segment.

    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
    Мария
    -1.05
    ฿
    -1.04
    Ẩ
    -1.03
    CUIT
    -1.02
    Марина
    -1.01
    Миха
    -0.98
    ivät
    -0.98
    Наталья
    -0.97
     OMIT
    -0.97
    好久
    -0.96
    POSITIVE LOGITS
    </h2>
    1.06
     chiedere
    0.97
    繰
    0.94
    FEBRUARY
    0.88
    ，「
    0.87
     inability
    0.87
    tink
    0.86
    乃是
    0.84
     then
    0.83
     préc
    0.83
    Activations Density 0.002%

    No Known Activations