© 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. 22-GEMMASCOPE-RES-131K
    7. 72235
    Prev
    Next
    INDEX
    Explanations

    me, you, us, contacting

    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
     will
    -1.31
     only
    -1.16
    They
    -1.05
     There
    -1.05
     If
    -1.04
     in
    -0.98
     Then
    -0.97
    T
    -0.96
     This
    -0.96
     These
    -0.95
    POSITIVE LOGITS
     us
    2.27
     me
    2.06
     our
    1.81
    เรา
    1.78
     you
    1.66
     μας
    1.59
    我們
    1.54
    我们
    1.46
     my
    1.43
     ours
    1.41
    Activations Density 0.029%

    No Known Activations