© 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. 10-GEMMASCOPE-RES-131K
    7. 12261
    Prev
    Next
    INDEX
    Explanations

    stack exchange site mechanics

    np_acts-logits-general · gemini-2.5-flash-lite

    words related to online forum or Q&A site interactions, particularly regarding reputation, voting, posting, and moderation activities.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     only
    -1.72
     ONLY
    -1.41
     perpetually
    -1.38
     misguided
    -1.34
     unrelenting
    -1.32
     relentlessly
    -1.30
    Only
    -1.29
     ALWAYS
    -1.28
     superbly
    -1.27
     freshly
    -1.27
    POSITIVE LOGITS
     they
    1.63
     amazing
    1.35
    measured
    1.32
     splendid
    1.32
    cript
    1.30
     such
    1.22
     terrific
    1.21
     amd
    1.21
    tellers
    1.20
     astounding
    1.18
    Activations Density 0.175%

    No Known Activations