© 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. 34-GEMMASCOPE-RES-131K
    7. 82391
    Prev
    Next
    INDEX
    Explanations

    certified credentials and designations

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

    The neuron fires strongly on all-capitalized sequences and acronyms (often organization names or titles) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     mini
    -0.73
    MO
    -0.73
     ti
    -0.73
     int
    -0.72
     gag
    -0.71
     disc
    -0.71
    Criteria
    -0.71
     inf
    -0.71
     young
    -0.70
     sea
    -0.70
    POSITIVE LOGITS
     Certified
    1.53
     designation
    1.43
     designations
    1.29
    Certified
    1.16
    designation
    1.16
     certified
    1.13
     Designation
    1.04
     credential
    0.99
     certifications
    0.96
     certification
    0.94
    Activations Density 0.026%

    No Known Activations