© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130564
    Prev
    Next
    INDEX
    Explanations

    urls with specific words

    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
     Dinas
    -1.38
     лесу
    -1.34
     💕
    -1.31
    たまに
    -1.30
    那你
    -1.30
    possibly
    -1.28
     prêtre
    -1.27
    ABULARY
    -1.27
     アウター
    -1.27
     😁
    -1.27
    POSITIVE LOGITS
     their
    1.98
     so
    1.94
     our
    1.74
     first
    1.63
     (
    1.59
     decided
    1.54
     really
    1.50
     very
    1.46
     ended
    1.45
     totally
    1.45
    Activations Density 0.015%

    No Known Activations