© 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. 46103
    Prev
    Next
    INDEX
    Explanations

    should hurt mercy justice may

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

    versatility, served, fascinating

    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
    故障
    0.43
    餐
    0.42
     gesch
    0.41
    恢复
    0.41
    維持
    0.40
     डाउट्स
    0.40
    生存
    0.39
     kennis
    0.39
    疯狂
    0.39
    冇
    0.39
    POSITIVE LOGITS
     Apl
    0.40
     કે
    0.39
     awaits
    0.39
     marrying
    0.39
     courthouse
    0.38
     Sebast
    0.38
     retiring
    0.38
    ונה
    0.38
     civic
    0.37
     anthropologist
    0.37
    Activations Density 0.000%

    No Known Activations