© 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. 41915
    Prev
    Next
    INDEX
    Explanations

    Ki-67 and prefixes

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

    The neuron identifies the Japanese syllable "ki" in various contexts, such as names, terms, and the Ki-67 protein marker.

    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
    ↵
    -3.98
    <em>
    -2.91
    l
    -2.77
    烀
    -2.77
    咴
    -2.70
     gewähr
    -2.53
    pecabe
    -2.48
    p
    -2.42
     高級
    -2.39
    寕
    -2.36
    POSITIVE LOGITS
    ことができました
    2.92
     يمكنك
    2.44
     If
    2.36
     he
    2.23
    使う
    2.22
    咄
    2.20
     Если
    2.19
    莅
    2.19
    раи
    2.17
    ?"
    2.16
    Activations Density 0.012%

    No Known Activations