© 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. 22-GEMMASCOPE-RES-131K
    7. 9485
    Prev
    Next
    INDEX
    Explanations

    possessive followed by 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
     of
    -1.27
     their
    -1.26
     sogenannte
    -1.15
     Merdeka
    -1.12
     ENERG
    -1.11
    hibits
    -1.09
    嘖
    -1.09
    ícia
    -1.09
     чле
    -1.09
    chable
    -1.08
    POSITIVE LOGITS
    balon
    1.30
    évêque
    1.29
     continuará
    1.26
     επίσης
    1.25
     semej
    1.22
    nagy
    1.17
    GRI
    1.13
     pudiera
    1.11
     entirety
    1.11
    Arsenic
    1.10
    Activations Density 0.054%

    No Known Activations