© 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. 74872
    Prev
    Next
    INDEX
    Explanations

    letters before parentheses or lists

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

    This neuron identifies standalone single-character or numeric tokens used as list/question item labels (e.g. “I”, “B”, “2”).

    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
     теперь
    -1.12
     هیچ
    -1.04
     Nó
    -1.01
    就不会
    -1.00
    dekat
    -1.00
    狮子
    -0.99
    asteroid
    -0.97
    ”？
    -0.97
    uangan
    -0.97
    }$.
    -0.96
    POSITIVE LOGITS
    着一个
    1.17
    During
    1.10
     Two
    1.08
     veneta
    1.07
    Although
    1.07
    了一眼
    1.05
     Three
    1.04
     During
    1.02
    After
    1.02
    繭
    1.02
    Activations Density 0.000%

    No Known Activations