© 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. 35618
    Prev
    Next
    INDEX
    Explanations

    numbered steps or sequences

    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
     our
    -1.54
     this
    -1.38
     these
    -1.28
     recent
    -1.25
     those
    -1.22
    annte
    -1.13
     kors
    -1.11
     also
    -1.09
    recent
    -1.05
     भी
    -1.04
    POSITIVE LOGITS
     then
    2.41
    然后
    1.52
     Then
    1.39
     następnie
    1.37
     afterwards
    1.35
    Then
    1.30
     steps
    1.30
     thereafter
    1.23
     vervolgens
    1.17
     THEN
    1.16
    Activations Density 0.006%

    No Known Activations