© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38647
    Prev
    Next
    INDEX
    Explanations

    names ending in -man, -old, -lock, -cher, -den, -rott

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

    The neuron fires on capitalized surnames of authors (i.e. last names) in bibliographic or citation contexts.

    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
    ...
    -1.36
    :
    -1.30
    ಠ
    -1.29
     de
    -1.25
     You
    -1.23
    ",
    -1.18
     simples
    -1.15
     chamado
    -1.15
     ต
    -1.13
    —
    -1.11
    POSITIVE LOGITS
     there
    1.34
     ragaz
    1.29
     takk
    1.19
     provence
    1.18
    ẵn
    1.18
     תמיד
    1.16
     tille
    1.14
     frites
    1.13
     周辺
    1.12
     glossy
    1.10
    Activations Density 0.113%

    No Known Activations