© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31758
    Prev
    Next
    INDEX
    Explanations

    real and imaginary parts

    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
     Baby
    -0.75
    eclipse
    -0.71
    jek
    -0.69
    readInt
    -0.69
     indictment
    -0.67
     திரு
    -0.66
    jago
    -0.66
    ಗ
    -0.66
    éfono
    -0.65
    zee
    -0.63
    POSITIVE LOGITS
     imaginary
    4.16
    imaginary
    3.50
     Imagin
    3.50
    Imaginary
    3.31
     imagination
    2.97
     imagin
    2.94
     IMAG
    2.88
     imagina
    2.86
    imag
    2.80
    Imagin
    2.80
    Activations Density 0.117%

    No Known Activations