© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180674
    Prev
    Next
    INDEX
    Explanations

    countdown with, Loved learning, manipulates, conventional meal

    np_acts-logits-general · gemini-2.5-flash-lite

    common english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ،
    0.64
     uncanny
    0.52
    ，
    0.49
    ，“
    0.49
    Social
    0.48
     الاجتماعية
    0.47
     errand
    0.45
     mindless
    0.45
     industrialists
    0.44
     whimsical
    0.44
    POSITIVE LOGITS
     хорошие
    0.55
     перемен
    0.51
    κου
    0.48
    ச்ச
    0.48
     sacrificed
    0.47
    餸
    0.47
     procedente
    0.46
    𝑧
    0.46
     conectado
    0.46
    শক্ত
    0.46
    Activations Density 0.001%

    No Known Activations