© 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. 34-GEMMASCOPE-RES-131K
    7. 2596
    Prev
    Next
    INDEX
    Explanations

    dead bodies

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

    references to discovering or finding dead bodies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    我慢
    -0.74
     Schild
    -0.74
     aktar
    -0.72
    typed
    -0.70
     stads
    -0.69
    脸上
    -0.69
     millioner
    -0.68
    larım
    -0.67
    uyucu
    -0.67
     électron
    -0.66
    POSITIVE LOGITS
     bodies
    5.09
     body
    4.78
     corpse
    3.70
     corpses
    3.63
     Bodies
    3.63
    body
    3.48
    bodies
    3.41
    Bodies
    3.39
    Body
    3.22
     Body
    3.19
    Activations Density 0.054%

    No Known Activations