© 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. 34-GEMMASCOPE-RES-131K
    7. 64118
    Prev
    Next
    INDEX
    Explanations

    bug report URLs or code snippets

    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
    上帝
    -0.75
    Đi
    -0.70
     rolex
    -0.70
    elyk
    -0.69
    äst
    -0.69
    レモン
    -0.69
     Öz
    -0.69
     Mackie
    -0.68
     Đi
    -0.67
    緣
    -0.67
    POSITIVE LOGITS
    研修
    0.73
     dumped
    0.71
    Curves
    0.69
     Dump
    0.65
    TEP
    0.65
     תפ
    0.65
    űr
    0.64
    kuuta
    0.64
    śnia
    0.63
    yr
    0.61
    Activations Density 0.068%

    No Known Activations