© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1648
    Prev
    Next
    INDEX
    Explanations

    cosmological topics and concepts

    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/layer_40_width_262k_l0_medium
    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
     অভ্যন্তরীণ
    0.47
    ┎
    0.47
    
    0.46
     tagReport
    0.45
    饲
    0.44
     Aeron
    0.44
    SleepHours
    0.43
    员
    0.43
    辄
    0.42
    衄
    0.42
    POSITIVE LOGITS
     cosmological
    1.23
     cosmology
    1.12
     Cosmology
    0.93
     cosm
    0.91
    宇宙
    0.89
     inflationary
    0.88
     cosmic
    0.87
     Cosm
    0.77
     kosm
    0.77
     dark
    0.76
    Activations Density 0.026%

    No Known Activations