© 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. 84514
    Prev
    Next
    INDEX
    Explanations

    thanks for

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

    The neuron consistently responds to the preposition “for.”

    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
     only
    -2.05
     by
    -1.53
     ONLY
    -1.50
     larger
    -1.48
     more
    -1.46
     several
    -1.44
     from
    -1.41
     one
    -1.40
     three
    -1.38
     some
    -1.38
    POSITIVE LOGITS
    はこの
    1.33
    がこの
    1.27
     biologie
    1.25
     inconvénients
    1.21
     dépenses
    1.20
     coûts
    1.20
     dommages
    1.18
     スリーブ
    1.17
    这次
    1.16
     pertes
    1.16
    Activations Density 0.006%

    No Known Activations