© 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. 131201
    Prev
    Next
    INDEX
    Explanations

    executive luxury garden games

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

    seeking reform

    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
     killed
    0.56
    n
    0.56
    sol
    0.54
     claiming
    0.51
     obligated
    0.50
    killed
    0.50
     prevented
    0.49
    net
    0.48
     righteous
    0.48
    posable
    0.48
    POSITIVE LOGITS
     건축
    0.55
     ভাবের
    0.54
     ক্ষেত্র
    0.52
     风
    0.51
     мебель
    0.51
    痈
    0.50
    阍
    0.49
     учащихся
    0.48
     équipements
    0.47
     lám
    0.47
    Activations Density 0.002%

    No Known Activations