© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41260
    Prev
    Next
    INDEX
    Explanations

    code or mathematical structure

    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
    .
    -1.92
     if
    -1.77
     requires
    -1.73
     Before
    -1.73
    -
    -1.63
    {
    -1.61
     If
    -1.59
    fficking
    -1.57
     There
    -1.55
     kupić
    -1.55
    POSITIVE LOGITS
    ="
    1.88
     delightfully
    1.84
     beautifully
    1.80
     momentous
    1.80
     และ
    1.77
    both
    1.76
     delightful
    1.73
     tremendous
    1.73
     astounding
    1.69
     giu
    1.68
    Activations Density 0.000%

    No Known Activations