© 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. 48542
    Prev
    Next
    INDEX
    Explanations

    javascript 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
    :[{
    -0.89
     東京
    -0.83
    ᴘ
    -0.81
    -0.79
    ;*/
    -0.78
    heden
    -0.73
     安
    -0.73
    JNI
    -0.72
    Escolha
    -0.72
    ]):
    -0.71
    POSITIVE LOGITS
     echocardio
    0.88
    typescript
    0.79
    ALLENG
    0.78
    本田
    0.78
    リーナ
    0.77
    龘
    0.77
     ACTUAL
    0.75
     Democrat
    0.74
    紧接着
    0.74
    оти
    0.74
    Activations Density 0.005%

    No Known Activations