© 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. 57310
    Prev
    Next
    INDEX
    Explanations

    but not

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

    Do you know about

    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
    创建一个
    0.50
     非
    0.48
    決定
    0.45
    必須
    0.45
     আক্রমণ
    0.45
    !!!");
    0.45
     없고
    0.45
    ungkinkan
    0.44
     이용해서
    0.44
     결정
    0.44
    POSITIVE LOGITS
    ।
    0.48
     Millennials
    0.47
     wyróż
    0.47
    .​
    0.46
     clichés
    0.46
     düşünüyorum
    0.45
     montrer
    0.44
     biomark
    0.44
     iStock
    0.44
     médias
    0.43
    Activations Density 0.000%

    No Known Activations