© 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. 21099
    Prev
    Next
    INDEX
    Explanations

    names of people

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

    The neuron fires on single-token capitalized surnames of well-known people (e.g. Robeson, Salonga, Szeryng).

    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
     pomys
    -1.56
    чені
    -1.41
     모두
    -1.33
     csomag
    -1.32
     Bachelor
    -1.32
     karty
    -1.31
     zespo
    -1.31
     jazdy
    -1.27
     $\
    -1.22
     zape
    -1.21
    POSITIVE LOGITS
     saranno
    1.34
     denso
    1.33
     mena
    1.31
     fati
    1.30
     bazar
    1.28
     prodi
    1.27
     metus
    1.27
     parma
    1.26
     produt
    1.26
     boxe
    1.25
    Activations Density 0.366%

    No Known Activations