© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101060
    Prev
    Next
    INDEX
    Explanations

    likely following auxiliary verbs

    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_10/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
    atikan
    -1.48
     garota
    -1.20
    мый
    -1.16
     nobre
    -1.16
     montanha
    -1.13
    TEC
    -1.11
    nienia
    -1.08
    </b>
    -1.07
    Laporan
    -1.06
    логии
    -1.05
    POSITIVE LOGITS
     likely
    1.48
    Likely
    1.47
    probably
    1.45
     может
    1.41
    Probably
    1.40
    likely
    1.40
     może
    1.38
     gdyby
    1.36
    可能
    1.34
     може
    1.34
    Activations Density 0.158%

    No Known Activations