© 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. 22-GEMMASCOPE-RES-131K
    7. 33228
    Prev
    Next
    INDEX
    Explanations

    afterward time sequence

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

    This neuron reliably lights up on mentions of the document’s main subject—its proper name or the pronouns referring back to that central entity.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    änien
    -1.06
    нача
    -1.05
    ♏
    -1.02
     norvég
    -0.95
    Already
    -0.94
    Yesterday
    -0.94
     Raton
    -0.93
    жела
    -0.93
     keempat
    -0.93
     janvier
    -0.93
    POSITIVE LOGITS
     then
    2.97
     subsequent
    2.75
     thereafter
    2.47
     subsequently
    2.39
     later
    2.28
    その後
    2.11
     afterwards
    1.96
     afterward
    1.78
     Subsequently
    1.69
     násled
    1.68
    Activations Density 0.064%

    No Known Activations