© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 78146
    Prev
    Next
    INDEX
    Explanations

    bubble popping

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

    more... solution

    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
     пород
    0.50
     ке
    0.47
    ה
    0.47
     пусть
    0.47
     сала
    0.46
     آدم
    0.46
     внутренней
    0.46
    一颗
    0.45
    맇
    0.45
     вечером
    0.44
    POSITIVE LOGITS
    sta
    0.57
    exam
    0.56
    le
    0.55
    ulator
    0.51
    setting
    0.51
    united
    0.49
    el
    0.49
    this
    0.48
    starter
    0.47
    ulation
    0.47
    Activations Density 0.000%

    No Known Activations