© 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. 150011
    Prev
    Next
    INDEX
    Explanations

    harming environmental

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

    code, JSON, options, events, technology

    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
    Negative Logits
     Ek
    0.55
     Yer
    0.48
    Ek
    0.47
     Yel
    0.46
    endeu
    0.43
     Kuk
    0.42
    teaser
    0.42
    k
    0.42
    廚
    0.41
    Enders
    0.41
    POSITIVE LOGITS
     legislatures
    0.65
     employees
    0.53
     defendant
    0.53
     policies
    0.52
    ΑΣ
    0.52
    Ⅼ
    0.52
     classrooms
    0.51
     universally
    0.51
     through
    0.50
     officials
    0.49
    Activations Density 0.001%

    No Known Activations