© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7350
    Prev
    Next
    INDEX
    Explanations

    expressing possibility or potential outcomes

    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
     are
    -1.91
     —
    -1.82
    zi
    -1.77
    ze
    -1.73
    be
    -1.69
    0
    -1.64
    an
    -1.64
     usando
    -1.59
    neling
    -1.57
    一根
    -1.55
    POSITIVE LOGITS
     tricky
    1.96
     there
    1.84
     if
    1.76
     because
    1.75
    ﾔ
    1.70
     contemplar
    1.68
     EVERY
    1.67
     來
    1.66
    when
    1.66
    ～～～
    1.66
    Activations Density 0.077%

    No Known Activations