© 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. 95651
    Prev
    Next
    INDEX
    Explanations

    that followed by a verb

    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
    andidaten
    -1.16
    efte
    -1.08
    ługość
    -1.07
     市场
    -1.05
     związ
    -1.02
     وتع
    -1.01
     RNAs
    -1.00
     Barça
    -0.99
    imir
    -0.98
    mlink
    -0.97
    POSITIVE LOGITS
     these
    1.39
     most
    1.26
     we
    1.24
    如此
    1.14
     the
    1.08
     keeps
    1.08
     matters
    1.01
     değil
    1.00
     I
    0.98
     आदि
    0.98
    Activations Density 0.012%

    No Known Activations