© 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. 34-GEMMASCOPE-RES-131K
    7. 90517
    Prev
    Next
    INDEX
    Explanations

    translation and scaling transformations

    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_34/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
    stepper
    -0.71
     approfon
    -0.69
     ufficio
    -0.67
     capitals
    -0.66
     lombok
    -0.66
     tenda
    -0.65
    unton
    -0.64
     spettacolo
    -0.63
     ない
    -0.63
    関節
    -0.63
    POSITIVE LOGITS
     translation
    3.52
     translate
    3.22
     translations
    3.19
     translated
    3.05
     Translation
    2.89
     Translate
    2.84
     translating
    2.81
    translation
    2.77
    Translate
    2.70
     shift
    2.69
    Activations Density 0.072%

    No Known Activations