© 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. 41084
    Prev
    Next
    INDEX
    Explanations

    MF followed by technical terms

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

    This neuron detects the standalone token “MF” in text (i.e. occurrences of the uppercase acronym “MF”).

    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
    }
    -3.02
     */
    -2.56
    0
    -2.55
     Oberfläche
    -2.45
     a
    -2.44
     {
    -2.41
    诳
    -2.34
     peut
    -2.33
     oder
    -2.31
    骉
    -2.25
    POSITIVE LOGITS
     This
    2.34
     Despite
    2.33
    Because
    2.33
    eeeee
    2.30
     icônes
    2.28
     OBJET
    2.22
     bahia
    2.22
    ‪.‬‬
    2.19
    Since
    2.19
    after
    2.14
    Activations Density 0.007%

    No Known Activations