© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 647
    Prev
    Next
    INDEX
    Explanations

    mass graves, burial sites

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

    content related to graves, burial grounds, mass graves, and remains of the deceased.

    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
     smoky
    -0.81
    enswert
    -0.80
    netinet
    -0.78
    accordion
    -0.74
     seizure
    -0.73
    thello
    -0.72
    urat
    -0.72
    solete
    -0.71
    ilat
    -0.71
    Justification
    -0.71
    POSITIVE LOGITS
     graves
    1.62
     unmarked
    1.60
     burial
    1.52
     mass
    1.36
     burials
    1.32
    mass
    1.22
     burying
    1.20
    Graves
    1.12
     buried
    1.09
    Mass
    1.08
    Activations Density 0.021%

    No Known Activations