© 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. 36540
    Prev
    Next
    INDEX
    Explanations

    package declarations, titles, or version counts

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

    This neuron fires on XML element names (e.g. the “Version” tag).

    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
    了一会儿
    -1.32
    鼍
    -1.28
     aussit
    -1.23
    臵
    -1.21
     proposent
    -1.21
     vogel
    -1.20
    frequently
    -1.17
     alkoh
    -1.15
    蛱
    -1.15
     suivent
    -1.13
    POSITIVE LOGITS
     and
    2.11
     in
    1.46
     battling
    1.21
     which
    1.17
    Rend
    1.14
     on
    1.12
     nestled
    1.12
     one
    1.11
     creates
    1.11
     went
    1.08
    Activations Density 0.000%

    No Known Activations