© 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. 22-GEMMASCOPE-RES-131K
    7. 12949
    Prev
    Next
    INDEX
    Explanations

    code and math constants

    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
     and
    -1.43
     سات
    -1.12
    ちゃんと
    -1.12
     موب
    -1.06
     ſame
    -1.05
    8
    -1.04
    4
    -1.04
     ständig
    -1.04
     Brings
    -1.03
    3
    -1.03
    POSITIVE LOGITS
    ਫ਼
    1.28
     uLocal
    1.06
     котором
    1.05
     (
    1.05
     its
    1.05
    krankungen
    1.03
     helyez
    1.03
    
    1.03
     "..\..\
    1.02
     становника
    1.02
    Activations Density 0.018%

    No Known Activations