© 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. 38651
    Prev
    Next
    INDEX
    Explanations

    control and 0/1 sequences

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

    The neuron strongly activates on all-caps tokens (i.e. acronyms or uppercase markers like “EOF,” “PBS,” “Con,” etc.).

    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
     and
    -0.93
    оборот
    -0.87
    チョイス
    -0.83
     damska
    -0.80
    sellors
    -0.80
     inför
    -0.79
    理工
    -0.79
    Not
    -0.79
     mniej
    -0.79
    rouw
    -0.78
    POSITIVE LOGITS
     pandemia
    1.07
     furia
    1.06
     tary
    1.05
     interieur
    1.02
     cortina
    1.02
     imun
    1.02
     stai
    1.02
     territ
    1.01
     lavander
    0.99
     pute
    0.98
    Activations Density 0.045%

    No Known Activations