© 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. 129202
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to specialized scientific terms—especially biomedical and biochemical jargon (e.g. “macrophage,” “cell,” chemical names, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    })}$
    -0.95
    fsch
    -0.87
     even
    -0.87
    }<\
    -0.86
     was
    -0.86
     hinter
    -0.85
     t
    -0.84
     could
    -0.84
    ksesta
    -0.84
     k
    -0.82
    POSITIVE LOGITS
     forskellige
    1.09
     разные
    1.02
     olika
    0.96
     suministros
    0.96
     båda
    0.95
     KILL
    0.90
    ทั้ง
    0.90
    ouvrir
    0.87
    levelse
    0.87
     její
    0.86
    Activations Density 0.174%

    No Known Activations