© 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. 60568
    Prev
    Next
    INDEX
    Explanations

    fc/ or fc

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

    The neuron strongly activates on occurrences of the token “fc,” for example in C++ include paths or namespace declarations.

    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
    er
    -2.70
    ⬈
    -2.63
    灃
    -2.48
    ྰ
    -2.38
    oncé
    -2.31
    ised
    -2.28
     púrpura
    -2.23
    ן
    -2.23
     titu
    -2.22
     feitas
    -2.22
    POSITIVE LOGITS
    d
    3.22
    }$
    3.00
    c
    2.77
    1
    2.75
    '
    2.73
    b
    2.50
    t
    2.41
    lgari
    2.25
    0
    2.25
    f
    2.20
    Activations Density 0.007%

    No Known Activations