© 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. 22-GEMMASCOPE-RES-131K
    7. 35264
    Prev
    Next
    INDEX
    Explanations

    necessity or consequence

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

    The neuron strongly activates on words that begin new sentences (e.g. capitalized “For,” “You,” “Then,” “In,” etc.).

    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
    Trying
    -1.03
    trying
    -0.99
    Surely
    -0.98
    Acab
    -0.92
     kaynağından
    -0.90
     بما
    -0.89
     Surely
    -0.88
     anymore
    -0.88
     herrera
    -0.87
     wanting
    -0.87
    POSITIVE LOGITS
    才行
    1.51
    才能
    1.50
     to
    1.38
     must
    1.32
     иначе
    1.03
     باید
    1.02
    해야
    1.01
     phải
    1.01
     so
    1.00
     jinak
    1.00
    Activations Density 0.141%

    No Known Activations