© 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. 34-GEMMASCOPE-RES-131K
    7. 81295
    Prev
    Next
    INDEX
    Explanations

    objective-c framework usage

    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_34/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
     velvety
    -0.85
    ayo
    -0.82
    是否
    -0.71
     hyperplasia
    -0.68
    CFR
    -0.67
     opposites
    -0.67
    日閲覧
    -0.65
    ि
    -0.65
    setAttribute
    -0.65
    Outros
    -0.65
    POSITIVE LOGITS
     placeholder
    0.81
    Scratch
    0.79
    bower
    0.77
    ᱒
    0.76
     bát
    0.76
     main
    0.76
    ступление
    0.76
    scratch
    0.75
    дій
    0.75
    lllllll
    0.74
    Activations Density 0.033%

    No Known Activations