© 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. 66208
    Prev
    Next
    INDEX
    Explanations

    body parts and health

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

    possessive pronouns (your, my, his) followed by body parts or personal items.

    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
    できれば
    -0.89
    Andres
    -0.85
     Heel
    -0.79
    لوار
    -0.77
    жается
    -0.75
     蕾
    -0.74
    ftan
    -0.74
     hochwer
    -0.73
     légitime
    -0.73
    ⎞
    -0.73
    POSITIVE LOGITS
     eyes
    0.99
    วง
    0.88
     breasts
    0.86
     lungs
    0.84
     mind
    0.84
     chromosomes
    0.84
     teeth
    0.84
     brain
    0.84
    ticus
    0.84
     wajah
    0.81
    Activations Density 0.135%

    No Known Activations