© 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. 12
    Prev
    Next
    INDEX
    Explanations

    phrases starting with prepositional words

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

    The neuron is looking for common English function tokens—particularly the past‐tense/participle suffix “-ed” and short prepositions or grammatical words like “with,” “to,” and “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
    っていたので
    -1.26
     it
    -1.22
     cebolla
    -1.21
     czter
    -1.16
     spolup
    -1.16
     dôle
    -1.16
     kilku
    -1.16
     pegatina
    -1.14
    えると
    -1.14
    corsi
    -1.13
    POSITIVE LOGITS
    ではありません
    1.16
     only
    1.16
    ?
    1.14
    kosti
    1.13
    只有
    1.02
     isn
    1.00
    ではない
    0.98
     GDP
    0.96
    حات
    0.95
    !
    0.95
    Activations Density 0.038%

    No Known Activations