© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67981
    Prev
    Next
    INDEX
    Explanations

    creates, examples, saving, before

    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
     
    -3.20
     éstas
    -3.02
     asust
    -2.84
     extremadamente
    -2.72
     "
    -2.70
     téc
    -2.66
     originalmente
    -2.61
     dán
    -2.55
     cómod
    -2.55
     éstos
    -2.50
    POSITIVE LOGITS
    衚
    2.88
    ।
    2.69
    ’
    2.56
    卨
    2.56
    胧
    2.56
    {\
    2.55
    т
    2.50
    这么多
    2.45
     公园
    2.44
    %。
    2.41
    Activations Density 0.001%

    No Known Activations