© 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. 34-GEMMASCOPE-RES-131K
    7. 107547
    Prev
    Next
    INDEX
    Explanations

    until followed by possessive pronoun

    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
     leurs
    -1.11
    の特徴
    -0.82
    Those
    -0.77
    ⋰
    -0.77
     Leurs
    -0.76
    都要
    -0.74
    Its
    -0.74
    öffentlichungen
    -0.73
    Our
    -0.72
     unserer
    -0.71
    POSITIVE LOGITS
     his
    2.48
     sua
    1.52
     своё
    1.38
     its
    1.38
     jego
    1.33
     его
    1.28
     swoją
    1.26
     your
    1.20
     своей
    1.18
     його
    1.18
    Activations Density 0.077%

    No Known Activations