© 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. 22-GEMMASCOPE-RES-131K
    7. 14
    Prev
    Next
    INDEX
    Explanations

    coming loose or detached

    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_22/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
     for
    -1.09
    how
    -1.05
    ESTADO
    -1.03
     esperança
    -1.02
     to
    -1.01
    new
    -0.92
    UNUSED
    -0.91
     πυ
    -0.91
     finally
    -0.90
     для
    -0.90
    POSITIVE LOGITS
     during
    1.44
     podczas
    1.24
     durante
    1.18
     أثناء
    1.09
     Durante
    1.05
     потеря
    1.02
     tijdens
    0.98
    omitempty
    0.96
    During
    0.91
     loose
    0.91
    Activations Density 0.058%

    No Known Activations