© 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. 74917
    Prev
    Next
    INDEX
    Explanations

    sequences ending in common terms

    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
     That
    -1.53
     Our
    -1.48
    boîte
    -1.42
    diez
    -1.37
     like
    -1.33
    montre
    -1.30
     or
    -1.27
    ácidos
    -1.27
     Время
    -1.27
     sebagaimana
    -1.25
    POSITIVE LOGITS
    </h3>
    1.34
    them
    1.23
    cause
    1.21
    whether
    1.19
    izate
    1.16
    plevel
    1.16
     حتی
    1.16
    老者
    1.16
    occasione
    1.13
    entown
    1.12
    Activations Density 0.096%

    No Known Activations