© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43263
    Prev
    Next
    INDEX
    Explanations

    amyloid precursor protein

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

    scientific and technical terminology, particularly within specialized fields like biochemistry, medicine, and computer science.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron responds to specialized technical or domain‐specific jargon terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     also
    -1.77
     afecto
    -1.70
     you
    -1.63
     then
    -1.55
     únicamente
    -1.45
     profumo
    -1.45
     entendimiento
    -1.44
     sujeto
    -1.43
     someone
    -1.41
     posibles
    -1.39
    POSITIVE LOGITS
    ❔
    1.74
     beber
    1.58
    👻
    1.41
    cended
    1.37
    Without
    1.36
    hamed
    1.34
     dava
    1.33
     vald
    1.30
     viera
    1.24
    🍜
    1.24
    Activations Density 1.114%

    No Known Activations