© 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. 76559
    Prev
    Next
    INDEX
    Explanations

    grammatical cases and agreement

    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
     perfecte
    -0.78
    purl
    -0.73
     dette
    -0.72
     :
    -0.72
    PASS
    -0.71
     passive
    -0.71
    MatButtonModule
    -0.70
    ども
    -0.69
    rire
    -0.68
     trembling
    -0.68
    POSITIVE LOGITS
     accus
    1.35
     gen
    1.30
     Nomin
    1.21
     nomin
    1.20
    Nomin
    1.18
     case
    1.07
    nomin
    1.05
    accus
    1.04
     oblique
    1.01
     possessive
    1.00
    Activations Density 0.038%

    No Known Activations