© 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. 13254
    Prev
    Next
    INDEX
    Explanations

    phrases like "this way"

    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
     vapore
    -1.45
    ورم
    -1.39
     hant
    -1.36
     cortina
    -1.34
    Cevap
    -1.34
    都能
    -1.32
    瞜
    -1.32
     kazak
    -1.31
     можуть
    -1.30
     cannes
    -1.30
    POSITIVE LOGITS
     '
    1.61
    “
    1.55
    er
    1.55
     kteří
    1.52
     которые
    1.48
     должны
    1.45
     ćwic
    1.42
     której
    1.42
    ons
    1.41
    </em>
    1.39
    Activations Density 0.031%

    No Known Activations