© 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. 2629
    Prev
    Next
    INDEX
    Explanations

    meat processing and animal preparation

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

    text related to meat processing, hunting, and animal butchering.

    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
    ună
    -0.88
     Namur
    -0.88
    lový
    -0.85
    脐
    -0.85
     conductas
    -0.84
     Dvor
    -0.84
    
    -0.83
     BIRTHDAY
    -0.82
     corral
    -0.82
     Lenovo
    -0.81
    POSITIVE LOGITS
     trophy
    1.26
     skin
    1.20
    trophy
    1.17
     tax
    1.11
     Tax
    1.09
     trophies
    1.07
     skinned
    1.01
     McKenzie
    0.93
     Trophy
    0.91
    Tax
    0.89
    Activations Density 0.007%

    No Known Activations