© 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. 22-GEMMASCOPE-RES-131K
    7. 14565
    Prev
    Next
    INDEX
    Explanations

    lists, legal, and studies

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

    The neuron fires on obituary notices, especially the phrasing of funeral service arrangements (e.g. “Services will be held at …”).

    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
    ledad
    -1.34
    neling
    -1.10
    sighted
    -1.09
    <eos>
    -1.08
    alism
    -1.06
    ateness
    -1.05
    níka
    -1.03
    かで
    -1.03
    iconCls
    -1.02
    assis
    -1.02
    POSITIVE LOGITS
    0.91
     japonaise
    0.90
     pravi
    0.90
    ませんか
    0.85
    ことも
    0.84
    作為
    0.84
     subsystems
    0.84
     vorbere
    0.83
     Municip
    0.83
     بعد
    0.83
    Activations Density 0.002%
    No Known Activations