© 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. 28397
    Prev
    Next
    INDEX
    Explanations

    actions ending in -ing

    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
     give
    -1.17
    !
    -1.15
     coopération
    -1.09
     allow
    -1.09
     also
    -1.06
     will
    -1.02
    z
    -1.02
    e
    -0.99
    ")==
    -0.98
    J
    -0.98
    POSITIVE LOGITS
     étant
    1.66
     being
    1.60
     sendo
    1.49
    being
    1.41
    おわりに
    1.38
    lâ
    1.27
    
    1.23
    venant
    1.21
     BEING
    1.20
     balón
    1.17
    Activations Density 0.043%

    No Known Activations