© 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. 85719
    Prev
    Next
    INDEX
    Explanations

    protein kinase A or C

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

    biochemical terms related to kinase proteins, particularly in scientific 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
     flyg
    -2.13
    '
    -2.13
     deceiving
    -2.11
    的就
    -2.08
    ांकि
    -2.06
     erbjuder
    -2.03
    d
    -2.02
     commencé
    -2.02
    ądze
    -1.98
     Süden
    -1.95
    POSITIVE LOGITS
     to
    2.38
    .
    2.06
    ある
    1.91
    قف
    1.91
    isière
    1.85
     pazienti
    1.82
     buscar
    1.77
    ことです
    1.75
    ujuk
    1.74
    盉
    1.72
    Activations Density 0.077%

    No Known Activations