© 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. 70607
    Prev
    Next
    INDEX
    Explanations

    specialized terms or technical jargon

    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
     if
    -0.88
    🦭
    -0.85
     completely
    -0.82
     politicians
    -0.82
     Drucker
    -0.81
     accountId
    -0.79
     essentially
    -0.79
     also
    -0.77
     getObject
    -0.77
     another
    -0.77
    POSITIVE LOGITS
    Quasi
    0.83
    nerv
    0.81
    STORY
    0.80
    Gris
    0.79
     terce
    0.79
    anias
    0.78
    dod
    0.78
    Yuk
    0.77
     мог
    0.77
    这里的
    0.77
    Activations Density 0.001%

    No Known Activations