© 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-65K
    7. 31586
    Prev
    Next
    INDEX
    Explanations

    publicly available information

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ond
    0.57
    are
    0.55
    ill
    0.54
    4
    0.53
    ich
    0.50
    és
    0.49
     आणि
    0.48
     Ми
    0.48
    Ş
    0.47
    kov
    0.47
    POSITIVE LOGITS
     eddies
    0.48
     inhibit
    0.48
     solutes
    0.48
     utterances
    0.48
     hydrolysis
    0.46
     reluctance
    0.46
     eluted
    0.46
     usefulness
    0.45
     alkene
    0.45
     spont
    0.45
    Activations Density 0.007%

    No Known Activations