© 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. 58979
    Prev
    Next
    INDEX
    Explanations

    portrait and portfolio usage

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

    The neuron fires on occurrences of the sequence “port­fol­io” (and very strongly on “Portfolio”/“Portfolios”) 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
     serpent
    -0.97
     porosity
    -0.91
     annehmen
    -0.90
    得知
    -0.90
    abı
    -0.90
     превос
    -0.90
    去做
    -0.90
     probate
    -0.89
     donné
    -0.88
    𝒆
    -0.86
    POSITIVE LOGITS
    ⋃
    1.00
    ogra
    0.98
    лем
    0.97
     zum
    0.96
    Meghan
    0.94
    𖣔
    0.93
    他又
    0.93
     ξ
    0.92
     Meghan
    0.92
     upsetting
    0.91
    Activations Density 0.016%

    No Known Activations