© 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. 22372
    Prev
    Next
    INDEX
    Explanations

    in order to

    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
     to
    -1.88
     encargada
    -1.52
    どうして
    -1.52
     cercana
    -1.51
     
    -1.46
     meistens
    -1.45
     mehrm
    -1.41
    𔘓
    -1.40
    どうやって
    -1.40
     =
    -1.40
    POSITIVE LOGITS
     hilsen
    1.73
     nacht
    1.72
     and
    1.66
    ۷
    1.64
    andte
    1.61
    не
    1.59
     personen
    1.58
    ۵
    1.55
     sientes
    1.55
     København
    1.53
    Activations Density 0.051%

    No Known Activations