© 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. 23820
    Prev
    Next
    INDEX
    Explanations

    return 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
    pozorn
    -0.92
     both
    -0.91
     acordo
    -0.84
    метри
    -0.84
    疫苗
    -0.82
     Beitrag
    -0.81
    генера
    -0.80
    kswagen
    -0.80
     their
    -0.80
     пальто
    -0.77
    POSITIVE LOGITS
     russischen
    1.05
    來的
    0.91
    WSGI
    0.90
    旁边
    0.88
    selectable
    0.83
     отец
    0.82
    用到
    0.82
     olduğunu
    0.82
     发表于
    0.82
    身上
    0.81
    Activations Density 0.003%

    No Known Activations