© 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. 84903
    Prev
    Next
    INDEX
    Explanations

    code constructs

    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
    thus
    -1.05
    Thus
    -0.92
     eingeführt
    -0.91
    潺
    -0.88
    ppar
    -0.88
     детского
    -0.88
    continued
    -0.87
    believe
    -0.86
    zdě
    -0.86
     fasting
    -0.86
    POSITIVE LOGITS
    <h3>
    1.00
     if
    0.88
    "){
    0.87
     with
    0.81
    uttaa
    0.80
     both
    0.79
     for
    0.78
     Posting
    0.75
    ){//
    0.75
    ={
    0.74
    Activations Density 0.007%

    No Known Activations