© 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. 20826
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations

    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
    e
    -3.30
    en
    -3.30
    ed
    -3.28
    er
    -3.25
    an
    -3.17
    ir
    -2.89
     portrayed
    -2.81
    ſam
    -2.77
    蜮
    -2.70
    ות
    -2.64
    POSITIVE LOGITS
     mögliche
    3.16
    ↵↵
    3.13
     breite
    3.11
     
    3.05
    </h3>
    2.91
     ähnliche
    2.91
     schwere
    2.88
    本当に
    2.88
     komplette
    2.88
     originalen
    2.81
    Activations Density 1.446%

    No Known Activations