© 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. 28339
    Prev
    Next
    INDEX
    Explanations

    regularly applying a constant vector

    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
     to
    -1.41
     abraço
    -1.09
    大さじ
    -1.08
    很快就
    -1.05
     provide
    -1.04
     estreia
    -1.03
     manhã
    -1.02
     include
    -1.02
     already
    -1.01
    ientôt
    -1.01
    POSITIVE LOGITS
    当店
    1.16
    ふと
    1.06
    私たち
    1.05
    粉色
    1.05
    ciendo
    1.04
     we
    1.04
    
    1.03
    เรา
    1.02
     vecteur
    1.02
     lác
    1.00
    Activations Density 0.001%

    No Known Activations