© 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. 331
    Prev
    Next
    INDEX
    Explanations

    specific instances

    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
     and
    -1.12
     another
    -1.05
    tismo
    -0.93
    Gilla
    -0.91
    (!__
    -0.88
     weitere
    -0.83
     other
    -0.83
    ritus
    -0.83
     denne
    -0.82
    暟
    -0.81
    POSITIVE LOGITS
     infatti
    1.78
     nämlich
    1.35
     totiž
    1.25
     bowiem
    1.21
     частности
    1.09
     namelijk
    1.02
     nemlig
    1.01
    Specifically
    1.00
     namely
    1.00
    dion
    1.00
    Activations Density 0.128%

    No Known Activations