© 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. 10-GEMMASCOPE-RES-131K
    4. 101637
    Prev
    Next
    INDEX
    Explanations

    letter B

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

    The neuron fires on standalone “B” (or “b”) tokens—that is, single‐letter tokens B/b.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    			
    -1.38
    蔓延
    -1.24
     and
    -1.24
    		
    -1.23
    Â
    -1.22
    бол
    -1.19
     by
    -1.16
    十五
    -1.16
     maart
    -1.15
    ваете
    -1.12
    POSITIVE LOGITS
    another
    1.43
     pretože
    1.35
     musíte
    1.23
     tasas
    1.22
     there
    1.21
     another
    1.20
     другая
    1.18
     extremely
    1.16
    是一個
    1.16
     geloof
    1.15
    Activations Density 0.277%

    No Known Activations