© 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. 74897
    Prev
    Next
    INDEX
    Explanations

    PHP session_start()

    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
     or
    -1.50
     from
    -1.30
     only
    -1.16
     because
    -1.13
    -
    -1.06
     most
    -1.04
     all
    -1.03
     on
    -1.02
     an
    -1.00
     companies
    -1.00
    POSITIVE LOGITS
     كلمة
    1.14
     pouvaient
    1.05
    干什么
    1.04
    皞
    0.98
    
    0.98
     aficionados
    0.98
    鹇
    0.97
    逦
    0.96
     grandiose
    0.95
    Елена
    0.95
    Activations Density 0.000%

    No Known Activations