© 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. 34-GEMMASCOPE-RES-131K
    7. 79256
    Prev
    Next
    INDEX
    Explanations

    coroner, death investigations

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

    locations or terms related to cemeteries, burial grounds, and memorial sites.

    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
    birthdate
    -0.73
     Josephus
    -0.72
     })
    -0.71
    Miracle
    -0.70
    litten
    -0.70
     UPSC
    -0.70
    োগ
    -0.69
     Silhouette
    -0.69
    𝜂
    -0.68
     imprison
    -0.68
    POSITIVE LOGITS
    urned
    0.81
     cry
    0.80
     baby
    0.78
     vault
    0.77
     uncon
    0.76
     vai
    0.74
     Baby
    0.73
    ोर्ट
    0.73
     dissent
    0.72
     Zoro
    0.71
    Activations Density 0.019%

    No Known Activations