© 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. 67877
    Prev
    Next
    INDEX
    Explanations

    youth and young people

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

    the neuron strongly activates on mentions of youth or young-related entities (e.g., “Youth,” “Young,” “Offenders Institution,” etc.).

    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
    on
    -1.27
    mathrm
    -1.07
     själ
    -1.06
    #%%
    -1.03
    遢
    -1.02
     decent
    -1.02
    is
    -1.00
     fulfills
    -0.99
     ögon
    -0.98
     ondu
    -0.97
    POSITIVE LOGITS
     youth
    1.34
     where
    1.28
    tzmann
    1.21
     conifers
    1.20
    תוח
    1.20
    ρίου
    1.18
    young
    1.18
    ută
    1.17
    riera
    1.16
    adoles
    1.16
    Activations Density 0.220%

    No Known Activations