© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 4941
    Prev
    Next
    INDEX
    Explanations

    surreal and dream-like descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     bounces
    0.63
    सबुक
    0.59
     PDF
    0.57
    PDF
    0.57
     pdf
    0.55
    pdf
    0.55
     payloads
    0.55
     bounce
    0.54
    ‮
    0.53
    Bounce
    0.52
    POSITIVE LOGITS
     Getty
    1.50
    Getty
    1.31
     iStock
    1.25
     Shutterstock
    1.23
     getty
    1.20
     alamy
    1.07
     shutterstock
    1.07
     dreamstime
    0.99
    istock
    0.96
     Photographer
    0.96
    Activations Density 0.268%

    No Known Activations