© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 10861
    Prev
    Next
    INDEX
    Explanations

    certified status or approval

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

    This neuron activates on occurrences of the word “certified.”

    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
     "
    -2.41
     $
    -2.34
     картинка
    -2.20
     utilisé
    -2.13
    ৢ
    -2.09
     So
    -2.06
     In
    -2.05
     combinación
    -2.05
    c
    -2.03
    埽
    -2.03
    POSITIVE LOGITS
    With
    3.38
    After
    3.23
    Before
    3.17
    Now
    3.16
    Despite
    3.09
    Because
    3.05
    Maybe
    3.02
    Without
    2.98
    Although
    2.98
    While
    2.94
    Activations Density 0.012%

    No Known Activations