© 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. 114199
    Prev
    Next
    INDEX
    Explanations

    administration arrived

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

    geopolitical consequences and impacts

    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
    illery
    0.46
     prepping
    0.43
    ാം
    0.43
    同时也
    0.41
     distancing
    0.40
     প্রথমবারের
    0.40
    娥
    0.40
     আত্ম
    0.40
    餾
    0.39
     పూర్తిగా
    0.39
    POSITIVE LOGITS
     achat
    0.46
    Genetic
    0.44
    が良い
    0.44
    가능
    0.43
    PHI
    0.43
    付近
    0.42
     Antwerp
    0.42
    Rub
    0.42
     important
    0.42
    ANC
    0.41
    Activations Density 0.001%

    No Known Activations