© 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. 67721
    Prev
    Next
    INDEX
    Explanations

    members and friends

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

    This neuron spotlights the standalone headings “Members” and “Friends” that label groups or lists of people.

    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
    d
    -3.25
    逦
    -2.75
    すでに
    -2.69
     pensar
    -2.50
    きちんと
    -2.39
     anteriormente
    -2.38
    朏
    -2.38
    "
    -2.36
    越大
    -2.34
    缡
    -2.34
    POSITIVE LOGITS
    ?”
    3.25
    淩
    3.08
    鹇
    2.92
    鿬
    2.83
    齜
    2.80
    Ꮉ
    2.72
    ro
    2.72
     westfalen
    2.67
    🩲
    2.64
    齮
    2.63
    Activations Density 0.007%

    No Known Activations