© 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. 10-GEMMASCOPE-RES-131K
    7. 10031
    Prev
    Next
    INDEX
    Explanations

    calcification

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

    The neuron detects words ending in "ification" or "ified", particularly 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
    ra
    -3.34
    </b>
    -2.88
    -
    -2.56
    al
    -2.56
     obtiene
    -2.44
    enablog
    -2.41
    ON
    -2.36
    am
    -2.28
    檮
    -2.25
    ра
    -2.22
    POSITIVE LOGITS
    ’
    3.05
    </h3>
    2.73
     didnt
    2.48
    诶
    2.45
    ＝＝＝＝
    2.45
    〜。
    2.39
    下一篇
    2.38
    桄
    2.34
    ᠸ
    2.28
    聍
    2.28
    Activations Density 0.039%

    No Known Activations