© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 1
    Prev
    Next
    INDEX
    Explanations

    creation, origin, or influence

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

    The neuron is highly sensitive to hyphens (dash characters) used to join or separate words.

    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
     to
    -1.16
    :
    -1.12
     topik
    -1.12
     it
    -1.09
     here
    -1.07
    女孩子
    -1.02
     potencial
    -0.97
    背影
    -0.97
    了自己的
    -0.97
    loss
    -0.97
    POSITIVE LOGITS
     ścian
    1.38
     billede
    1.22
     største
    1.21
    féle
    1.14
    \#:
    1.13
     XXXIV
    1.07
     eneste
    1.06
    りましたが
    1.05
     XXXII
    1.05
     twarzy
    1.05
    Activations Density 0.142%

    No Known Activations