© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 102144
    Prev
    Next
    INDEX
    Explanations

    Nurses and gasoline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Convention
    0.46
    녹
    0.45
     Convention
    0.44
    綠
    0.43
    緑
    0.42
    convention
    0.41
    绿
    0.41
     зелены
    0.40
    十二
    0.39
    Soviet
    0.37
    POSITIVE LOGITS
     Chelsea
    0.61
     Manning
    0.61
    Chelsea
    0.55
    രിക
    0.40
     gels
    0.39
     Rangers
    0.38
    թ
    0.37
     വീഡിയോ
    0.37
     Harvesting
    0.37
    ্বার
    0.36
    Activations Density 0.001%

    No Known Activations