© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 72161
    Prev
    Next
    INDEX
    Explanations

    with or without

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

    This neuron is highly responsive to the preposition “with.”

    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
    秶
    -1.33
     our
    -1.23
     my
    -1.16
    神
    -1.10
     frauen
    -1.08
    cinq
    -1.08
     pesso
    -1.07
     соответствии
    -1.05
     relevante
    -1.04
     Siapa
    -1.04
    POSITIVE LOGITS
     with
    1.24
     connotation
    1.18
    "");
    1.17
    ."/
    1.12
    россий
    1.12
    觑
    1.10
    esgue
    1.08
    ração
    1.08
    tispiece
    1.07
     pengobatan
    1.06
    Activations Density 0.107%

    No Known Activations