© 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. 70655
    Prev
    Next
    INDEX
    Explanations

    associating preceding words with subsequent nouns

    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
    蓑
    -0.94
     appartement
    -0.93
     domaines
    -0.91
     collectons
    -0.91
     pneu
    -0.91
    SOBRE
    -0.91
    ziers
    -0.91
    民众
    -0.91
     TODOS
    -0.90
    virano
    -0.89
    POSITIVE LOGITS
     its
    1.09
     cumplir
    0.97
     altrett
    0.94
     it
    0.94
     rispet
    0.93
    ((&
    0.93
     ponieważ
    0.90
     other
    0.89
     localidades
    0.89
     Provide
    0.88
    Activations Density 0.199%

    No Known Activations