© 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. 103941
    Prev
    Next
    INDEX
    Explanations

    words ending in en

    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
    dogs
    -1.01
    capaian
    -0.96
    té
    -0.95
    ds
    -0.92
    doc
    -0.89
    tes
    -0.89
    grö
    -0.88
    dog
    -0.86
    gro
    -0.85
     addition
    -0.84
    POSITIVE LOGITS
    omics
    1.01
    ews
    0.98
    sitive
    0.98
    adering
    0.93
    ius
    0.91
    ni
    0.90
    so
    0.90
    ning
    0.83
    digkeit
    0.80
     Commandments
    0.80
    Activations Density 0.280%

    No Known Activations