© 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. 22-GEMMASCOPE-RES-131K
    7. 12524
    Prev
    Next
    INDEX
    Explanations

    process and assessment details

    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_22/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
     dAtA
    -1.03
    zele
    -1.00
    ઃ
    -0.99
    licherweise
    -0.98
     controla
    -0.97
    ってみました
    -0.97
    freude
    -0.94
     prin
    -0.91
    𝒆
    -0.90
    <0xA7>
    -0.90
    POSITIVE LOGITS
     your
    1.58
     soyez
    1.20
     déterminer
    1.16
     menengah
    1.13
     Then
    1.13
     tracción
    1.13
     then
    1.13
    település
    1.09
     vendeurs
    1.05
     the
    1.04
    Activations Density 0.029%

    No Known Activations