© 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. 98423
    Prev
    Next
    INDEX
    Explanations

    English Language

    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
     so
    -1.32
     that
    -1.13
     because
    -1.12
     first
    -0.98
     would
    -0.97
     solely
    -0.92
    When
    -0.92
    <b>
    -0.91
     you
    -0.90
     after
    -0.89
    POSITIVE LOGITS
     thậm
    1.13
     hatta
    1.11
     diferite
    1.05
     HIP
    1.04
    Intrinsic
    1.02
     trám
    1.02
     EVEN
    1.00
     навіть
    0.98
     manger
    0.98
     Mende
    0.98
    Activations Density 0.000%

    No Known Activations