© 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. 10-GEMMASCOPE-RES-131K
    7. 42900
    Prev
    Next
    INDEX
    Explanations

    biological changes

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

    The neuron detects the word "alterations" and variations of this term in scientific and medical contexts.

    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_10/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
    鐿
    -2.67
     memasukkan
    -2.58
     mengel
    -2.55
    عنی
    -2.47
    ！"
    -2.42
    慊
    -2.42
    felpa
    -2.41
    眎
    -2.38
    
    -2.38
    岿
    -2.34
    POSITIVE LOGITS
    .
    3.34
    ↵
    3.23
    n
    2.98
    it
    2.83
     he
    2.53
    which
    2.52
    但是在
    2.48
    1
    2.41
     }
    2.39
    or
    2.34
    Activations Density 0.008%

    No Known Activations