© 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. 72024
    Prev
    Next
    INDEX
    Explanations

    missing persons and wanted individuals

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

    This neuron fires on tokens that are part of detailed personal or demographic descriptions (e.g. gender, race, age, height, weight) in people‐profile passages.

    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
    by
    -1.03
    visor
    -0.94
     \
    -0.94
    f
    -0.92
     enjoy
    -0.92
     never
    -0.92
    ne
    -0.91
    Vo
    -0.90
     ਪ੍ਰ
    -0.90
    v
    -0.90
    POSITIVE LOGITS
    áñez
    1.27
    τικός
    1.27
     Lidé
    1.15
    恻
    1.13
    чества
    1.13
     urgently
    1.12
     henkilö
    1.09
    利
    1.09
     fortalec
    1.09
    綣
    1.09
    Activations Density 0.046%

    No Known Activations