© 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. 170425
    Prev
    Next
    INDEX
    Explanations

    point and click escape game

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

    interacting elements and actions

    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
     urgent
    0.51
     fug
    0.46
     rek
    0.46
     graduating
    0.46
     shadowy
    0.46
     ሆ
    0.45
     पढ़ाई
    0.45
     grad
    0.44
    Fb
    0.44
     SOCIAL
    0.44
    POSITIVE LOGITS
    时候
    0.54
    并且
    0.52
    业主
    0.48
    myd
    0.47
    意义
    0.46
    的样子
    0.42
    容
    0.42
     代码
    0.42
     ولكن
    0.42
    我们可以
    0.42
    Activations Density 0.001%

    No Known Activations