© 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. 10-GEMMASCOPE-RES-131K
    7. 128575
    Prev
    Next
    INDEX
    Explanations

    paraffin-embedded

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

    The neuron detects the word "paraffin" in scientific contexts, particularly in tissue preparation and laboratory methods.

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

    The neuron specifically fires on mentions of “paraffin” (as in paraffin‐embedded or paraffin‐fixed specimens).

    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
     Schiffe
    -2.30
     kecuali
    -2.19
    rairie
    -2.16
    轳
    -2.16
     estatua
    -2.13
    lapia
    -2.11
    韞
    -2.11
    ATELY
    -2.06
    というと
    -2.02
    icksburg
    -1.99
    POSITIVE LOGITS
     '
    3.47
     uſ
    2.20
    ers
    2.17
    埽
    2.14
    r
    2.14
     grecque
    2.09
     «
    2.05
     chrétienne
    2.05
    ),
    2.03
     `
    2.03
    Activations Density 0.001%

    No Known Activations