© 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. 70847
    Prev
    Next
    INDEX
    Explanations

    phosphorylation

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

    terms related to protein phosphorylation and kinase activity in biochemical processes.

    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
    v
    -2.58
     Of
    -2.44
    al
    -2.33
    ra
    -2.22
    t
    -2.19
     como
    -2.09
     de
    -2.08
     you
    -2.08
     '.
    -2.05
    he
    -2.02
    POSITIVE LOGITS
    <bos>
    2.59
     帅气
    2.31
    趼
    2.31
    轫
    2.31
    衚
    2.20
    
    2.16
    曖
    2.14
    鱘
    2.13
    OUTUBE
    2.09
     花朵
    2.08
    Activations Density 0.047%

    No Known Activations