© 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. 39276
    Prev
    Next
    INDEX
    Explanations

    afterwards, post, aftermath, hindsight

    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
    Encyklopedia
    -1.06
     amikor
    -0.98
    zką
    -0.98
     currently
    -0.97
     years
    -0.97
     current
    -0.94
     chré
    -0.94
     Recently
    -0.93
    hintText
    -0.92
    ¤
    -0.92
    POSITIVE LOGITS
     afterwards
    1.40
     retrospect
    1.38
     aftermath
    1.33
     afterward
    1.27
    後日
    1.22
     hindsight
    1.12
     post
    1.11
     lendemain
    1.10
     IBOutlet
    1.08
    Takk
    1.03
    Activations Density 0.131%

    No Known Activations