© 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. 9522
    Prev
    Next
    INDEX
    Explanations

    rare or rarity

    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
     inescapable
    0.55
    half
    0.55
     inescap
    0.54
    noop
    0.51
     частично
    0.51
     partially
    0.50
    था
    0.50
    ])):
    0.50
    热门
    0.48
     করিতেছি
    0.48
    POSITIVE LOGITS
     rare
    3.50
    Rare
    3.23
     Rare
    3.11
     rarity
    3.02
    rare
    3.00
     rarer
    2.97
     rarely
    2.95
     Rarely
    2.92
     rares
    2.83
     rarest
    2.80
    Activations Density 0.398%

    No Known Activations