© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123952
    Prev
    Next
    INDEX
    Explanations

    numerical references

    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
     và
    -1.73
     wondrous
    -1.61
     my
    -1.61
     myriad
    -1.55
     renowned
    -1.55
     hugely
    -1.55
     trois
    -1.55
     senza
    -1.53
    ",
    -1.52
     —
    -1.51
    POSITIVE LOGITS
     always
    1.59
    Following
    1.52
    There
    1.51
     всегда
    1.48
    You
    1.44
    During
    1.42
     ALWAYS
    1.41
     ayakkabı
    1.40
     allow
    1.40
     製品
    1.38
    Activations Density 0.017%

    No Known Activations