© 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. 60307
    Prev
    Next
    INDEX
    Explanations

    background

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    bindingNavigator
    -0.77
     Arche
    -0.73
    bunifu
    -0.72
    ッコ
    -0.71
    mentar
    -0.71
    gste
    -0.70
    ーカー
    -0.70
     realtor
    -0.69
     Alde
    -0.69
     spurt
    -0.69
    POSITIVE LOGITS
     background
    6.97
    background
    5.59
    Background
    5.06
     Background
    5.03
     backgrounds
    4.25
     BACKGROUND
    4.25
    背景
    4.06
    BACKGROUND
    3.98
     Hintergrund
    3.86
     foreground
    3.56
    Activations Density 0.150%

    No Known Activations