© 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. 60607
    Prev
    Next
    INDEX
    Explanations

    telecommunications recommendations

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

    The neuron is detecting mentions of technical telecom/Internet protocols or standards (especially uppercase acronyms and their spelled‐out expansions).

    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
    itorious
    -0.74
     białym
    -0.73
     MEMS
    -0.70
    θή
    -0.69
     antenna
    -0.69
    ضية
    -0.68
    uF
    -0.68
    bergement
    -0.68
    crowned
    -0.67
     Eigenschaften
    -0.66
    POSITIVE LOGITS
     Recommendations
    0.94
    Recommendations
    0.94
     RECOMMENDATIONS
    0.85
    recommendations
    0.82
     recommendations
    0.81
    Vide
    0.80
     superconducting
    0.80
     Recommendation
    0.79
     SVD
    0.79
    Fax
    0.78
    Activations Density 0.037%

    No Known Activations