© 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. 10-GEMMASCOPE-RES-131K
    4. 86936
    Prev
    Next
    INDEX
    Explanations

    current, present, and recent time

    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_10/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
     then
    -1.56
    ">
    -1.52
    }$
    -1.40
     eignet
    -1.38
    もう一度
    -1.35
    _
    -1.30
    .".
    -1.30
    					
    -1.27
    \_
    -1.26
     menjalankan
    -1.25
    POSITIVE LOGITS
     لديك
    1.22
    Więcej
    1.16
     祝
    1.14
    Niveau
    1.10
     and
    1.08
    Sabes
    1.08
     меня
    1.07
    Kullan
    1.05
    herz
    1.05
    Тема
    1.04
    Activations Density 0.260%

    No Known Activations