© 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. 11257
    Prev
    Next
    INDEX
    Explanations

    linking verbs and common phrases

    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
     or
    -1.80
     from
    -1.43
     first
    -1.39
     even
    -1.22
     which
    -1.16
     before
    -1.12
     other
    -1.07
     .....
    -1.07
     exquisite
    -1.05
     oraz
    -1.04
    POSITIVE LOGITS
     totiž
    1.77
     so
    1.49
     bowiem
    1.23
    isn
    1.21
    を行い
    1.20
    这么
    1.16
     zwar
    1.15
     olduğ
    1.15
    obviously
    1.14
    cusa
    1.12
    Activations Density 0.044%

    No Known Activations