© 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. 589
    Prev
    Next
    INDEX
    Explanations

    not enough

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

    The neuron is detecting numeric literal tokens—especially multi‐digit and floating‐point constants—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
     sempat
    -0.97
    がある
    -0.94
     will
    -0.94
     masih
    -0.93
     можно
    -0.87
    Cata
    -0.87
    それでも
    -0.86
     akibat
    -0.86
     also
    -0.85
     still
    -0.84
    POSITIVE LOGITS
     insufficient
    1.20
     too
    1.16
     недоста
    1.14
     lacks
    1.13
     lack
    1.05
     neither
    1.04
     not
    1.00
     नहीं
    0.99
     olmayan
    0.96
    ไม่
    0.94
    Activations Density 0.004%

    No Known Activations