© 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. 39893
    Prev
    Next
    INDEX
    Explanations

    past possessive pronouns + noun

    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
     for
    -1.78
     unserer
    -1.14
     для
    -1.08
     with
    -1.07
     to
    -1.07
     recipients
    -1.02
     of
    -1.02
     subject
    -0.98
     from
    -0.95
    もあって
    -0.93
    POSITIVE LOGITS
     sobą
    1.15
    这段
    1.05
    {
    
    1.02
     comanda
    1.01
     ktoś
    1.01
     udział
    0.98
     coût
    0.95
     Siria
    0.94
    Ἡ
    0.93
     работе
    0.92
    Activations Density 0.045%

    No Known Activations