© 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. 15950
    Prev
    Next
    INDEX
    Explanations

    legal decision or court ruling

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

    The neuron strongly activates on very high‐frequency function words (articles and common prepositions) such as “the,” “a,” and “to.”

    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
    がなく
    -1.09
    товая
    -0.99
     “
    -0.96
    0
    -0.96
    each
    -0.95
    i
    -0.94
     '
    -0.94
     strikingly
    -0.94
     ᾿
    -0.94
     işe
    -0.93
    POSITIVE LOGITS
     on
    1.23
     Before
    1.21
     After
    1.20
    ַּ
    1.13
    adilan
    1.13
    Rozm
    1.11
     senjata
    1.10
    Китай
    1.09
    ּוֹ
    1.09
     pemerintah
    1.05
    Activations Density 0.175%

    No Known Activations