© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68679
    Prev
    Next
    INDEX
    Explanations

    a type category

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

    The neuron fires on instances of the field name “type” (e.g. in JSON or XML metadata attributes).

    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
     firft
    -1.36
    与此同时
    -1.32
    但是在
    -1.29
    [+]
    -1.28
    所以在
    -1.27
    issauga
    -1.27
    这让
    -1.24
     alfo
    -1.23
     Arki
    -1.20
    而后
    -1.20
    POSITIVE LOGITS
    throated
    1.27
     segura
    1.16
     azonban
    1.16
    Před
    1.15
    </h5>
    1.14
    artney
    1.11
     corregir
    1.11
    Cartney
    1.11
     они
    1.11
     jeho
    1.11
    Activations Density 0.017%

    No Known Activations