© 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. 28457
    Prev
    Next
    INDEX
    Explanations

    math relation `number - number`

    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
     Societies
    -0.86
    <blockquote>
    -0.85
    事態
    -0.81
     when
    -0.80
     with
    -0.79
     without
    -0.79
    Je
    -0.76
    Restaurant
    -0.76
    靭
    -0.76
     (
    -0.75
    POSITIVE LOGITS
    λύ
    1.04
    accor
    1.02
    インチ
    0.98
    ➅
    0.96
    tiéndose
    0.95
    inspir
    0.95
     seleccione
    0.93
     encabez
    0.93
     entfernt
    0.93
     ciertamente
    0.93
    Activations Density 0.001%

    No Known Activations