© 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. 38440
    Prev
    Next
    INDEX
    Explanations

    autophagy and autopsy

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

    The neuron detects words related to autophagy, including "autophagy," "autophagic," and "autopsied/autopsies."

    oai_token-act-pair · claude-3-7-sonnet-20250219
    Triggered by @neilrathi
    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
    Negative Logits
     &
    -2.11
    靫
    -2.09
    ଞ
    -2.09
    ровании
    -2.05
     to
    -2.02
    Ꮞ
    -1.75
    咘
    -1.73
    沕
    -1.73
    </em>
    -1.72
    щем
    -1.71
    POSITIVE LOGITS
    ↵
    2.70
     inauguración
    2.36
    {
    2.28
     современных
    2.20
     notch
    2.17
     feiert
    2.16
     imprisoned
    2.13
    }
    2.08
     использования
    2.06
    ”-
    2.06
    Activations Density 0.008%

    No Known Activations