© 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. 67633
    Prev
    Next
    INDEX
    Explanations

    sentence endings and conjunctions

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

    This neuron responds to semantically salient, content-heavy words (the key topic or domain–specific keywords) in the text.

    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
     которых
    -1.34
     которые
    -1.28
    izados
    -1.18
     then
    -1.17
     mereka
    -1.16
     serem
    -1.09
    belline
    -1.05
    vestidos
    -1.04
     themselves
    -1.02
     quien
    -1.02
    POSITIVE LOGITS
     its
    2.13
     there
    1.73
    Its
    1.51
     every
    1.21
    そのため
    1.19
     دارای
    1.13
    There
    1.12
    許多
    1.12
     where
    1.10
    仕方ない
    1.10
    Activations Density 0.074%

    No Known Activations