© 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. 79993
    Prev
    Next
    INDEX
    Explanations

    XML key-value pairs

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

    The neuron fires on the empty‐parameter parentheses “()” that mark function or method declarations/calls.

    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
     their
    -1.75
    
    -1.25
    Их
    -1.14
    ściu
    -1.13
    Aktual
    -1.10
    heureusement
    -1.09
    ⊰
    -1.05
     they
    -1.05
    Kondisi
    -1.05
     If
    -1.03
    POSITIVE LOGITS
     angepasst
    1.20
     gezogen
    1.19
     and
    1.16
     aktualisiert
    1.09
     tomando
    1.06
    ruary
    1.04
     אלה
    1.02
     áng
    1.01
     دنیا
    1.00
     mended
    1.00
    Activations Density 0.001%

    No Known Activations