© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38702
    Prev
    Next
    INDEX
    Explanations

    end of sentence or list item

    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
     then
    -1.34
     Then
    -1.27
     especially
    -1.09
     worst
    -1.03
    女性の
    -1.02
     also
    -0.97
    栩
    -0.94
     THEN
    -0.93
    Тогда
    -0.91
    Then
    -0.91
    POSITIVE LOGITS
     it
    1.76
     you
    1.31
    它
    1.29
     Please
    1.28
     please
    1.26
    Please
    1.07
     outras
    1.07
    Noten
    1.05
     clearColor
    1.04
     its
    1.03
    Activations Density 0.139%

    No Known Activations