© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92350
    Prev
    Next
    INDEX
    Explanations

    randomly assigned

    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
    Цель
    -0.88
    Ст
    -0.77
     فراهم
    -0.77
     Forbes
    -0.76
    uert
    -0.71
    Син
    -0.71
    Веду
    -0.70
    Сам
    -0.69
    Наша
    -0.69
     Sib
    -0.69
    POSITIVE LOGITS
     assigned
    6.13
     assign
    5.59
    assigned
    4.88
     assignment
    4.88
    assign
    4.78
     assigning
    4.75
     Assign
    4.66
    Assign
    4.59
     assigns
    4.53
    Assigned
    4.41
    Activations Density 0.145%

    No Known Activations