© 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. 10-GEMMASCOPE-RES-131K
    7. 229
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and related 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_10/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
     splend
    -1.36
     to
    -1.34
     would
    -1.30
    。
    -1.30
    //!
    -1.26
     in
    -1.22
     only
    -1.22
     referido
    -1.19
    名称
    -1.14
     brevis
    -1.14
    POSITIVE LOGITS
     essentielle
    1.59
    rocks
    1.34
    before
    1.27
    without
    1.27
     otra
    1.25
    though
    1.20
    through
    1.19
     grises
    1.19
    стоит
    1.18
     chois
    1.17
    Activations Density 0.023%

    No Known Activations