© 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. 99317
    Prev
    Next
    INDEX
    Explanations

    AFC, ABA

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

    The main thing this neuron does is detect occurrences of the acronym “AFC.”

    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
    裢
    -3.13
    衕
    -2.73
     ſtate
    -2.55
    ,’
    -2.55
    驺
    -2.48
    ’，
    -2.47
    .
    -2.45
    酲
    -2.42
     brancas
    -2.39
    屃
    -2.39
    POSITIVE LOGITS
    u
    2.80
    uellement
    2.55
    able
    2.55
     октя
    2.52
     две
    2.44
    </b>
    2.38
     BOTH
    2.36
     {
    2.34
    </u>
    2.34
    </h4>
    2.22
    Activations Density 0.006%

    No Known Activations