© 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. 100
    Prev
    Next
    INDEX
    Explanations

    conjunctions and disjunctions

    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
     pratiquement
    -0.92
    IMENTS
    -0.82
     courte
    -0.82
     корот
    -0.81
    OREA
    -0.81
    settes
    -0.79
     parlant
    -0.79
    potentially
    -0.79
    okości
    -0.79
    ecuzione
    -0.79
    POSITIVE LOGITS
     other
    1.03
     zumindest
    1.03
     serious
    0.91
     large
    0.87
     substantial
    0.86
     хотя
    0.85
     radically
    0.85
     significant
    0.84
     lesser
    0.84
     highly
    0.82
    Activations Density 0.151%

    No Known Activations