© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 24723
    Prev
    Next
    INDEX
    Explanations

    raw materials

    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
    Negative Logits
     ST
    0.43
    agle
    0.42
     এস
    0.39
    葩
    0.38
     কঠিন
    0.38
     Pref
    0.37
    avourite
    0.37
     पार्टी
    0.37
     urbano
    0.37
    Stadt
    0.37
    POSITIVE LOGITS
     material
    0.64
     materials
    0.49
     материала
    0.47
     Material
    0.47
     मटेरियल
    0.45
     materi
    0.45
    材
    0.44
    Material
    0.44
     materialize
    0.43
     materiale
    0.42
    Activations Density 0.022%

    No Known Activations