© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71825
    Prev
    Next
    INDEX
    Explanations

    citations with [@bib]

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

    The neuron activates on numeric citations or reference numbers (e.g. the numbers following citation markers in brackets).

    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
    itaji
    -1.34
     {
    
    
    -1.21
    providedIn
    -1.18
    ⁦
    -1.18
    atação
    -1.14
    лії
    -1.13
    LOADED
    -1.12
    ;;)
    -1.11
    летний
    -1.10
    elsif
    -1.09
    POSITIVE LOGITS
    3
    1.37
    6
    1.34
    ↵↵
    1.26
    8
    1.19
    7
    1.16
    4
    1.15
     PROFES
    1.09
    ~、
    1.05
    1
    1.05
    9
    1.04
    Activations Density 0.033%

    No Known Activations