© 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. 103213
    Prev
    Next
    INDEX
    Explanations

    user roles and status

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

    The neuron fires strongly on forum user rank labels and titles (e.g. “Member,” “Senior Member,” “Newbie,” etc.).

    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
     Overnight
    -0.79
    ✭✭
    -0.77
     duffel
    -0.74
     Athlete
    -0.73
     lexic
    -0.73
    precedented
    -0.71
     Mamma
    -0.69
    Classe
    -0.68
     Dota
    -0.68
     Elected
    -0.68
    POSITIVE LOGITS
    ₁(
    0.95
     absl
    0.85
    atical
    0.79
     scha
    0.76
    strong
    0.76
     reference
    0.75
    GtkWidget
    0.73
     but
    0.73
    czyk
    0.73
    oused
    0.71
    Activations Density 0.045%

    No Known Activations