© 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. 130505
    Prev
    Next
    INDEX
    Explanations

    Akt pathway

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

    This neuron activates for references to the PI3K (phosphatidylinositol 3-kinase) signaling pathway in biological 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
    j
    -1.66
    ak
    -1.66
    .’”
    -1.63
    st
    -1.61
     figlio
    -1.59
    ps
    -1.53
    ’.”
    -1.53
            
    -1.52
    al
    -1.51
    ci
    -1.48
    POSITIVE LOGITS
    gencias
    1.68
    stornos
    1.67
    ஂ
    1.62
     madres
    1.56
    财富
    1.51
    螣
    1.51
    reté
    1.48
    Tú
    1.48
     inflict
    1.48
     cubanos
    1.46
    Activations Density 0.033%

    No Known Activations