© 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. 14915
    Prev
    Next
    INDEX
    Explanations

    governance and management

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

    The neuron lights up on key content‐bearing words—especially nouns and proper names that identify the main entities or concepts in a passage.

    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
    ğe
    -1.10
     repeatedly
    -1.01
    Before
    -1.01
    Every
    -0.99
    المنا
    -0.97
     πρώ
    -0.97
    いかがでしょうか
    -0.97
     noiembrie
    -0.96
     begrenzt
    -0.95
    Hentet
    -0.94
    POSITIVE LOGITS
     control
    1.19
     respon
    1.16
     turma
    1.14
    manage
    1.11
     infrar
    1.10
     responsab
    1.06
    着一个
    1.05
     geven
    1.03
     diriger
    1.00
     وتح
    1.00
    Activations Density 0.053%

    No Known Activations