© 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. 103617
    Prev
    Next
    INDEX
    Explanations

    initialized updates

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

    explaining states and dependencies

    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
     marital
    0.48
     สู
    0.47
     puso
    0.47
     sveik
    0.46
     parede
    0.46
     tentar
    0.46
     cambiar
    0.45
     কারো
    0.45
     citas
    0.45
    鰥
    0.45
    POSITIVE LOGITS
     initialized
    0.46
     initially
    0.46
     OK
    0.46
    古
    0.46
    </h2>
    0.44
     Gore
    0.44
     evenly
    0.44
     Oct
    0.44
     apparently
    0.44
     Holl
    0.44
    Activations Density 0.000%

    No Known Activations