© 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. 11282
    Prev
    Next
    INDEX
    Explanations

    if youor Albert Freedman

    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
     mengumumkan
    -1.33
     WTF
    -1.13
    Voltaje
    -1.08
    pats
    -1.08
     هؤلاء
    -1.07
     '';
    
    -1.06
    Ḡ
    -1.06
    liun
    -1.06
     ersten
    -1.05
     stupid
    -1.05
    POSITIVE LOGITS
     your
    2.20
     you
    1.59
    your
    1.52
     currently
    1.48
    的话
    1.40
    您
    1.33
     manifestación
    1.29
    您的
    1.27
    you
    1.26
    :"-
    1.26
    Activations Density 0.061%

    No Known Activations