© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 65902
    Prev
    Next
    INDEX
    Explanations

    university of

    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
    をしています
    -1.10
     inneces
    -1.02
     fluxo
    -0.94
    ご了承ください
    -0.93
    西装
    -0.92
     ждут
    -0.92
     playera
    -0.89
    を行います
    -0.89
    怎样
    -0.88
     leggera
    -0.88
    POSITIVE LOGITS
     of
    5.44
     ऑफ
    1.09
     geweldige
    1.07
     prachtig
    1.03
     agregó
    0.96
    عرِّف
    0.96
    ркут
    0.96
    ของ
    0.95
    tube
    0.92
     College
    0.92
    Activations Density 0.014%

    No Known Activations