© 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. 118135
    Prev
    Next
    INDEX
    Explanations

    translation and interpreter services

    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
    plash
    -0.79
    csname
    -0.77
    '%(
    -0.76
     шкаф
    -0.76
    关心
    -0.74
     overclock
    -0.74
     otor
    -0.72
    匝
    -0.72
     aperta
    -0.72
     MONDAY
    -0.71
    POSITIVE LOGITS
     interpreters
    3.50
     interpreter
    3.47
     interpreting
    3.00
     Interpre
    2.98
     interpretation
    2.92
     Interpreter
    2.89
    interpreter
    2.78
    Interpre
    2.67
    Interpreter
    2.66
    interpre
    2.63
    Activations Density 0.023%

    No Known Activations