© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26407
    Prev
    Next
    INDEX
    Explanations

    SQL query execution

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

    This neuron detects PHP’s object‐member access operator (`->`).

    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
    อื่น
    -1.27
    ariConfig
    -1.27
     anderen
    -1.25
     blessé
    -1.24
     cuarent
    -1.13
     apareció
    -1.13
     Gedichte
    -1.13
     Näch
    -1.12
     the
    -1.12
     other
    -1.09
    POSITIVE LOGITS
    They
    1.25
    他們
    1.22
     они
    1.21
    G
    1.20
     вони
    1.12
     Они
    1.06
     They
    1.05
    讴
    1.04
                    
    1.02
     року
    1.02
    Activations Density 0.004%

    No Known Activations