© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49814
    Prev
    Next
    INDEX
    Explanations

    argument meaning, type, or context

    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
    ]
    -1.18
    ’
    -1.06
    ત્ર
    -0.98
    owany
    -0.96
    оргаш
    -0.96
    发表于
    -0.95
    a
    -0.95
    ACKNOWLEDGMENTS
    -0.93
    Zubereitung
    -0.92
    has
    -0.91
    POSITIVE LOGITS
    ative
    2.41
     about
    1.62
     against
    1.49
    ativeness
    1.39
    ATIVE
    1.35
     that
    1.30
    ation
    1.27
     for
    1.24
     ARG
    1.22
     AGAINST
    1.19
    Activations Density 0.016%

    No Known Activations