© 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. 34243
    Prev
    Next
    INDEX
    Explanations

    continuation or addition

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

    The neuron strongly activates on capitalized tokens denoting proper names or specialized terms.

    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
     then
    -1.21
     außerdem
    -1.13
     anschließend
    -1.09
     therefore
    -1.08
     daarna
    -1.05
     kemudian
    -1.05
    znál
    -1.04
     ママ
    -1.04
     others
    -1.03
     Inoltre
    -1.02
    POSITIVE LOGITS
     again
    2.25
     Again
    2.08
    こちらも
    2.00
    Again
    1.93
    again
    1.66
     опять
    1.59
    これも
    1.57
     ebenfalls
    1.44
    こちらは
    1.43
     снова
    1.41
    Activations Density 0.013%

    No Known Activations