© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9366
    Prev
    Next
    INDEX
    Explanations

    expressing personal understanding or hope

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     было
    0.57
     произошло
    0.57
     দেখা
    0.56
     возникает
    0.55
     suspicions
    0.54
     была
    0.54
     acontecimientos
    0.53
    脣
    0.53
     conseguiu
    0.52
     كانوا
    0.52
    POSITIVE LOGITS
     hope
    0.80
     hoffe
    0.80
     know
    0.79
     apologize
    0.76
     sorry
    0.70
    hope
    0.63
    know
    0.63
     swear
    0.63
     think
    0.61
     apolog
    0.61
    Activations Density 0.081%

    No Known Activations