© 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. 79590
    Prev
    Next
    INDEX
    Explanations

    degree of physical properties

    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
    などが
    -1.72
    などを
    -1.67
    doesn
    -1.55
     APPELLANT
    -1.54
    ebly
    -1.51
    mbal
    -1.47
    なども
    -1.47
    個人的には
    -1.45
    seems
    -1.45
     decidedly
    -1.43
    POSITIVE LOGITS
     unrelenting
    1.60
     or
    1.54
     time
    1.52
     Although
    1.48
     There
    1.45
     unwavering
    1.45
     burgeoning
    1.44
     Combining
    1.44
     it
    1.42
    場所で
    1.39
    Activations Density 0.063%

    No Known Activations