© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103875
    Prev
    Next
    INDEX
    Explanations

    negative emotions and states

    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_10/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
     decenas
    -1.41
     argument
    -1.37
    𐐪
    -1.32
     advantage
    -1.31
    ἀ
    -1.30
    线条
    -1.30
    FFFFFFFF
    -1.27
    動機
    -1.27
     purposes
    -1.25
     Tahun
    -1.25
    POSITIVE LOGITS
     to
    2.16
     that
    1.38
     for
    1.20
     awakeFromNib
    1.14
     of
    1.14
     sés
    1.12
     such
    1.09
    glected
    1.09
    这些
    1.09
     définir
    1.07
    Activations Density 0.166%

    No Known Activations