© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13965
    Prev
    Next
    INDEX
    Explanations

    cyclin and cell cycle control

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

    cell cycle regulatory proteins like cyclins, kinases, and cell cycle phase indicators.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects mentions of cyclin proteins (e.g. “cyclin A,” “cyclin D1,” and related CDKs) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    [].
    -1.50
     scris
    -1.48
    捋
    -1.37
     podéis
    -1.37
    元々
    -1.34
    一点点
    -1.30
     volontà
    -1.29
     womit
    -1.28
     Existing
    -1.27
     ------
    -1.27
    POSITIVE LOGITS
     הם
    1.38
     voor
    1.36
    igens
    1.26
    milch
    1.26
    liebe
    1.25
     飲
    1.20
     Zuid
    1.20
     mereka
    1.19
    sätzlich
    1.19
     estrogen
    1.18
    Activations Density 0.071%

    No Known Activations