© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34302
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by nouns

    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
     only
    -1.21
    ловой
    -1.05
    勇者
    -1.01
    CreateInfo
    -0.99
    any
    -0.99
    ⎝
    -0.97
    뿐
    -0.96
    зира
    -0.94
    and
    -0.93
    ը
    -0.93
    POSITIVE LOGITS
     respective
    2.78
    各自
    2.13
     their
    1.99
     jeweiligen
    1.97
    respective
    1.89
     themselves
    1.86
     respectivos
    1.84
     respectively
    1.80
    respectively
    1.80
    それぞれ
    1.76
    Activations Density 0.025%

    No Known Activations