© 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. 22-GEMMASCOPE-RES-131K
    7. 34278
    Prev
    Next
    INDEX
    Explanations

    famous surnames

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

    This neuron activates on capitalized proper nouns, especially well‐known surnames or brand names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    g
    -1.52
    V
    -1.52
    P
    -1.49
     is
    -1.39
    N
    -1.35
    h
    -1.32
    L
    -1.30
    f
    -1.29
    E
    -1.29
    v
    -1.28
    POSITIVE LOGITS
    här
    1.52
    красивые
    1.50
    corrhi
    1.49
     pás
    1.47
     éte
    1.46
    LANTA
    1.45
     achet
    1.43
     ſet
    1.41
     cerah
    1.40
     cepillo
    1.38
    Activations Density 0.085%

    No Known Activations