© 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. 91356
    Prev
    Next
    INDEX
    Explanations

    must be or retain

    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
     those
    -1.01
     buruk
    -0.94
     Sú
    -0.94
    szt
    -0.92
     leveraging
    -0.91
     inmig
    -0.90
     paredes
    -0.89
     their
    -0.89
    NFTs
    -0.88
     reducing
    -0.88
    POSITIVE LOGITS
     be
    1.91
     is
    1.09
    y
    1.03
    o
    0.94
    a
    0.94
    not
    0.93
    찬
    0.89
    ar
    0.89
     être
    0.86
    oma
    0.85
    Activations Density 0.004%

    No Known Activations