© 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. 14743
    Prev
    Next
    INDEX
    Explanations

    mc and mr prefixes

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

    The neuron responds to two‐letter tokens consisting of “m” plus another consonant—specifically the tokens “mr” and “mc.”

    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
    o
    -3.20
     ``
    -3.08
     `
    -2.25
     &#
    -2.22
    焄
    -2.17
    </h3>
    -2.16
     virtudes
    -2.11
    鋲
    -2.08
     pesky
    -2.06
     мозга
    -2.05
    POSITIVE LOGITS
    ATION
    2.83
    妩
    2.59
    which
    2.50
    輒
    2.50
    ING
    2.50
    to
    2.48
    栳
    2.31
    媃
    2.30
    鱨
    2.30
    塒
    2.22
    Activations Density 0.004%

    No Known Activations