© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108792
    Prev
    Next
    INDEX
    Explanations

    pil leading to words like pilocarpine or PIL import

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

    words beginning with "pil" like "pilot", "pilhofer", "pilocarpine", and "piling".

    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
     connu
    -0.80
    lift
    -0.72
     Gurgaon
    -0.69
     lift
    -0.68
     críticas
    -0.66
    Nobody
    -0.65
     тру
    -0.64
     nobody
    -0.63
     dziecko
    -0.63
    ייל
    -0.63
    POSITIVE LOGITS
     pil
    1.16
     Pil
    1.14
    pili
    0.97
    PIL
    0.96
    Pil
    0.94
     PIL
    0.94
    stände
    0.93
     Pill
    0.88
     pilo
    0.85
    pil
    0.83
    Activations Density 0.020%

    No Known Activations