© 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. 66667
    Prev
    Next
    INDEX
    Explanations

    positional and what follows

    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
    憷
    -1.69
     společnosti
    -1.68
     his
    -1.66
    \_\_
    -1.63
     \&
    -1.63
     spoluprá
    -1.60
    pantalones
    -1.55
     Zutaten
    -1.55
     bekämp
    -1.54
    \_
    -1.51
    POSITIVE LOGITS
    はこんな感じ
    1.30
     roca
    1.27
     all
    1.27
     Godt
    1.25
    pity
    1.24
     Tutti
    1.23
    Thus
    1.23
     eer
    1.22
     selva
    1.22
     Nieuws
    1.21
    Activations Density 0.003%

    No Known Activations