© 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. 65950
    Prev
    Next
    INDEX
    Explanations

    comparing elements or data

    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
    ญี่ป
    -1.05
     repentance
    -1.01
     mici
    -1.01
    咝
    -1.01
    ंत्री
    -1.00
    贍
    -1.00
     palanca
    -1.00
    şağı
    -0.98
     gewöhnlich
    -0.98
     división
    -0.97
    POSITIVE LOGITS
     against
    1.86
     with
    1.80
     different
    1.73
     apples
    1.52
     to
    1.49
     between
    1.45
     compare
    1.41
     favorably
    1.38
    Different
    1.32
     how
    1.30
    Activations Density 0.092%

    No Known Activations