© 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. 68257
    Prev
    Next
    INDEX
    Explanations

    room description features

    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
     anunció
    -1.79
     nació
    -1.56
     celebró
    -1.52
     reveló
    -1.52
     suelen
    -1.52
     différentes
    -1.51
     durante
    -1.51
     salieron
    -1.48
     différents
    -1.46
     både
    -1.44
    POSITIVE LOGITS
     and
    2.03
     still
    1.51
    .
    1.49
    ！"
    1.27
     all
    1.26
     "
    1.21
     took
    1.21
    帶
    1.20
     has
    1.18
     had
    1.18
    Activations Density 0.010%

    No Known Activations