© 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. 67494
    Prev
    Next
    INDEX
    Explanations

    deliberate action or purpose

    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
    結局
    -1.01
     lunghezza
    -0.84
     adequate
    -0.82
    Vrij
    -0.81
     miel
    -0.78
     these
    -0.78
    檜
    -0.78
     adequately
    -0.77
     disappointing
    -0.76
    解决了
    -0.76
    POSITIVE LOGITS
     challenge
    1.20
    故意
    1.19
    challenge
    1.09
     purposely
    1.06
     volontaire
    1.05
    random
    1.03
     bewusst
    1.03
     randomly
    1.02
     deliberately
    1.01
     intentionally
    0.98
    Activations Density 0.172%

    No Known Activations