© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 48122
    Prev
    Next
    INDEX
    Explanations

    molecule, proteins, orbit, magnetic

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

    scientific and technical concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     plethora
    0.64
     WITH
    0.59
     cca
    0.58
     ибо
    0.58
     simplistic
    0.53
     В
    0.53
     avec
    0.52
     altres
    0.52
     আমার
    0.52
     SS
    0.52
    POSITIVE LOGITS
     bakter
    0.59
     sogenannten
    0.59
     nanotubes
    0.57
     sogenannte
    0.54
    量子
    0.52
     photons
    0.52
     peneliti
    0.52
    －
    0.52
     nanoparticles
    0.51
     sogen
    0.50
    Activations Density 0.130%

    No Known Activations