© 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. 34-GEMMASCOPE-RES-131K
    4. 60699
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and determiners

    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_34/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
    タコ
    -1.36
     souvent
    -1.30
     wacky
    -1.30
    関連リンク
    -1.22
     goofy
    -1.22
    镲
    -1.20
     estadísticas
    -1.19
    齮
    -1.19
     ludicrous
    -1.19
     vérifier
    -1.19
    POSITIVE LOGITS
     its
    3.72
     other
    3.59
     their
    2.72
     his
    2.08
     других
    2.06
     all
    1.93
     diğer
    1.86
     others
    1.81
     دیگر
    1.78
     innych
    1.75
    Activations Density 0.135%

    No Known Activations