© 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. 28586
    Prev
    Next
    INDEX
    Explanations

    often occurring descriptions

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

    This neuron specifically fires on frequency-indicating adverbs (e.g. “often”).

    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
     everyone
    -1.27
     all
    -1.20
     everybody
    -1.16
     when
    -1.15
     this
    -1.11
     overall
    -1.06
     anyone
    -1.05
     seraient
    -1.04
    鷙
    -1.03
     orice
    -1.01
    POSITIVE LOGITS
     sogar
    1.53
     даже
    1.41
     bahkan
    1.38
     incluso
    1.31
     even
    1.24
     nawet
    1.20
     anche
    1.16
     también
    1.13
     zelfs
    1.13
     dessutom
    1.09
    Activations Density 0.089%

    No Known Activations