© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27348
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
     wciąż
    -1.16
     Cómo
    -1.15
     сейчас
    -1.05
     begint
    -1.05
    диви
    -1.03
     Tamaño
    -1.02
    heyd
    -1.02
    washingtonpost
    -1.01
     fréquemment
    -1.01
     pourriez
    -1.00
    POSITIVE LOGITS
    暧
    1.22
    sizePolicy
    1.18
     ...............
    1.13
     وزار
    1.10
     ??????
    1.05
    centro
    1.04
    rungen
    1.04
     péché
    1.02
     elétrico
    1.02
    baine
    1.02
    Activations Density 0.002%

    No Known Activations