© 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. 55720
    Prev
    Next
    INDEX
    Explanations

    We statements

    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
     as
    -0.96
    Huhu
    -0.92
    garder
    -0.88
     Handlungen
    -0.82
    独特
    -0.81
    Каждый
    -0.80
    طفى
    -0.80
    🇲
    -0.77
    ROUTINE
    -0.77
    Тема
    -0.76
    POSITIVE LOGITS
     recomienda
    1.31
     recommend
    1.24
     previously
    1.08
    そろそろ
    1.06
     exklu
    1.05
     vám
    1.05
     all
    1.03
     artikelen
    1.02
    previously
    0.99
     mohl
    0.98
    Activations Density 0.029%

    No Known Activations