© 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. 31-GEMMASCOPE-2-RES-262K
    7. 109633
    Prev
    Next
    INDEX
    Explanations

    molecules and atoms

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    developed
    0.50
     $)$
    0.47
     ένα
    0.46
     amassed
    0.46
     reaffirmed
    0.46
     protein
    0.45
     appreciable
    0.45
     patty
    0.44
    ciendo
    0.44
     inducible
    0.44
    POSITIVE LOGITS
     النموذج
    0.47
     modelos
    0.47
    /
    0.47
     modele
    0.46
    为了
    0.43
     differ
    0.42
    த்
    0.42
    的模型
    0.42
     disting
    0.42
     模型
    0.41
    Activations Density 0.009%

    No Known Activations