© 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. 117257
    Prev
    Next
    INDEX
    Explanations

    provided that

    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
     природе
    -0.81
     مرگ
    -0.79
     reizen
    -0.76
    OuterClass
    -0.75
    ngo
    -0.75
    ージャ
    -0.75
    xhttp
    -0.75
     TextField
    -0.75
    бак
    -0.74
    voye
    -0.73
    POSITIVE LOGITS
    if
    0.93
     erfü
    0.79
     zamiast
    0.77
    rough
    0.74
    每個
    0.73
    Diret
    0.73
    чне
    0.71
     tenere
    0.70
    如果不是
    0.69
    串
    0.69
    Activations Density 0.009%

    No Known Activations