© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91082
    Prev
    Next
    INDEX
    Explanations

    concerns and questions

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

    storage space, beginners, modules

    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
    Negative Logits
    &
    0.54
     &
    0.50
     !==
    0.46
    ashed
    0.45
     qualifier
    0.45
     gen
    0.44
     focus
    0.43
     view
    0.43
     queried
    0.43
     "
    0.43
    POSITIVE LOGITS
    সিডেন্ট
    0.57
     Regeneration
    0.54
    <unused635>
    0.54
     आता
    0.53
    strukt
    0.53
     Jahrze
    0.52
     அள
    0.50
    ძლიათ
    0.50
    omerase
    0.50
    ometro
    0.50
    Activations Density 0.000%

    No Known Activations