© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 27948
    Prev
    Next
    INDEX
    Explanations

    variable assignments

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

    The neuron activates on isolated mathematical identifiers—single‐letter variables (like x, y, R, G) and numeric constants.

    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
    AxisSize
    -0.80
    Exeunt
    -0.79
    Spells
    -0.76
    hdysval
    -0.76
    Sí
    -0.75
     refused
    -0.72
    ználat
    -0.72
     😉
    -0.71
    Jegyzőkönyv
    -0.71
     wijze
    -0.70
    POSITIVE LOGITS
    ximity
    0.85
    getSystemService
    0.83
     impresora
    0.83
     estranho
    0.83
     suivant
    0.83
     NOVEMBER
    0.82
    КП
    0.82
    
    0.80
    Junk
    0.80
    November
    0.80
    Activations Density 0.049%

    No Known Activations