© 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. 130665
    Prev
    Next
    INDEX
    Explanations

    possessive particle or related descriptor

    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
    のほうが
    -1.23
    ことも
    -1.20
    事が
    -1.13
    際は
    -1.13
    的过程中
    -1.10
    INSEE
    -1.09
     gesprek
    -1.09
    方には
    -1.08
    になれば
    -1.07
     iedereen
    -1.05
    POSITIVE LOGITS
    嘅
    1.24
    의
    1.21
     的
    1.17
    的
    1.09
    sendMessage
    1.07
     À
    1.05
    の
    1.05
    Ⅷ
    1.02
    ның
    1.01
    connects
    1.01
    Activations Density 0.005%

    No Known Activations