© 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. 67301
    Prev
    Next
    INDEX
    Explanations

    concerned that

    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
    してます
    -1.03
    べし
    -1.02
     same
    -1.02
     certain
    -1.00
     می‌توانید
    -0.95
     único
    -0.94
    わかります
    -0.94
     diversa
    -0.93
    んでる
    -0.92
    只需
    -0.92
    POSITIVE LOGITS
     that
    2.66
    ที่จะ
    1.10
    が
    1.09
     lectores
    1.07
    ¡¡¡
    1.04
    kts
    1.03
     jajaja
    1.03
    șe
    1.01
    Configurator
    0.98
    يتم
    0.96
    Activations Density 0.034%

    No Known Activations