© 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. 272
    Prev
    Next
    INDEX
    Explanations

    colon followed by new phrase

    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
     for
    -1.28
    عکس
    -1.22
     any
    -1.19
     also
    -1.14
     other
    -1.12
     my
    -1.11
     these
    -1.11
     it
    -1.09
     g
    -1.02
     It
    -1.02
    POSITIVE LOGITS
     Figura
    1.24
    reportWebVitals
    1.15
     membrana
    1.11
     inaugura
    1.10
     asfal
    1.09
     rezer
    1.09
    AHUL
    1.08
     abus
    1.07
     asisten
    1.06
     termos
    1.05
    Activations Density 0.152%

    No Known Activations