© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67489
    Prev
    Next
    INDEX
    Explanations

    API keys and managed services

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

    The neuron detects numeric constants (especially floating-point literals) in code or configuration snippets.

    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
     and
    -1.20
     Ordens
    -1.10
     setelah
    -1.09
     εί
    -1.05
     will
    -1.02
    ۟
    -1.02
     nuestra
    -1.02
     katholischen
    -1.00
    十五
    -1.00
    ığımız
    -0.99
    POSITIVE LOGITS
    ̵
    1.24
     שלהם
    1.15
    Managed
    1.09
    ╒
    1.09
    depends
    1.05
    managed
    1.02
    
    1.01
    becomes
    0.98
    Mui
    0.97
    knows
    0.96
    Activations Density 0.050%

    No Known Activations