© 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. 112809
    Prev
    Next
    INDEX
    Explanations

    change [determiner] [noun]

    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
    甃
    -1.88
     gebeten
    -1.80
    色々な
    -1.72
     They
    -1.72
    狨
    -1.66
    ﹍﹍
    -1.65
    ྵ
    -1.65
    色んな
    -1.63
     them
    -1.61
    黑衣
    -1.61
    POSITIVE LOGITS
     has
    1.84
     if
    1.73
    </h5>
    1.71
    </b>
    1.68
     &
    1.67
     the
    1.63
     which
    1.59
    نز
    1.58
    ‧
    1.57
    ).-
    1.55
    Activations Density 0.027%

    No Known Activations