© 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. 71308
    Prev
    Next
    INDEX
    Explanations

    IF followed by UP

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

    The neuron never fires (all its activations are zero), so it isn’t detecting any pattern—it’s effectively a “dead” neuron.

    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
     enorme
    -0.96
     pasteles
    -0.95
    จริง
    -0.94
    Šaltiniai
    -0.91
    siębior
    -0.90
    mohon
    -0.90
    สำหรับ
    -0.88
    ①
    -0.88
    Fans
    -0.88
    5
    -0.85
    POSITIVE LOGITS
     with
    1.10
     pertaining
    1.04
     miliardi
    1.00
     and
    0.99
    Kilde
    0.99
    了下去
    0.96
     about
    0.94
     profondità
    0.94
     that
    0.92
     usati
    0.92
    Activations Density 0.000%

    No Known Activations