© 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. 26793
    Prev
    Next
    INDEX
    Explanations

    code structure and commands

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

    The neuron fires on object member-access expressions (e.g. tokens appearing after “.” or “->” in code).

    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
     inond
    -2.00
     parfü
    -2.00
     célè
    -1.96
    dengan
    -1.85
     nadru
    -1.84
     fidé
    -1.84
     geschenk
    -1.80
    rechten
    -1.78
     rése
    -1.77
     parfüm
    -1.76
    POSITIVE LOGITS
    v
    1.94
    w
    1.82
     all
    1.81
     now
    1.81
     not
    1.80
    e
    1.77
     actually
    1.76
     set
    1.75
    z
    1.73
     get
    1.71
    Activations Density 0.004%

    No Known Activations