© 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. 73122
    Prev
    Next
    INDEX
    Explanations

    download a title

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

    This neuron fires on words that label or call out online document‐access actions or sections—e.g. “online,” “download,” “excerpt,” “description.”

    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
    Ні
    -0.96
    (^^)
    -0.95
     محفوظة
    -0.93
     many
    -0.93
    Съ
    -0.92
    êque
    -0.91
    nių
    -0.90
    リューション
    -0.90
    ėje
    -0.90
     häufig
    -0.90
    POSITIVE LOGITS
     of
    1.34
     Петро
    1.02
    綺麗に
    1.02
     ọ
    0.94
     있으며
    0.93
    ligheter
    0.92
     поводу
    0.91
     amazingly
    0.91
     REALLY
    0.91
     unbelievably
    0.90
    Activations Density 0.001%

    No Known Activations