© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1251
    Prev
    Next
    INDEX
    Explanations

    states of being

    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
     кө
    -1.01
     galima
    -0.94
    ستان
    -0.89
    ниці
    -0.84
     PRESENTED
    -0.82
    irmish
    -0.79
    shiro
    -0.76
    люб
    -0.75
    чика
    -0.75
    пу
    -0.75
    POSITIVE LOGITS
     being
    6.72
    Being
    4.72
    being
    4.53
     Being
    4.44
     быть
    4.00
     להיות
    3.92
     essere
    3.78
     BEING
    3.66
     becoming
    3.50
     être
    3.39
    Activations Density 0.150%

    No Known Activations