© 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. 22-GEMMASCOPE-RES-131K
    4. 75172
    Prev
    Next
    INDEX
    Explanations

    type of object

    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
     RECOMEND
    -1.00
    റ്
    -0.94
    Transk
    -0.93
     выбирать
    -0.89
    .")]
    -0.89
    něte
    -0.89
    žnost
    -0.88
    رسد
    -0.88
     ?</
    -0.87
    زال
    -0.85
    POSITIVE LOGITS
     of
    1.12
     from
    1.09
    rès
    1.00
     who
    0.93
     seorang
    0.93
     type
    0.91
     category
    0.90
    porus
    0.90
     outra
    0.88
    rati
    0.88
    Activations Density 0.113%

    No Known Activations