© 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. 78
    Prev
    Next
    INDEX
    Explanations

    punctuation after terms like essence or circle

    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
     illetve
    0.44
     _)
    0.42
     অতঃপর
    0.42
    并且
    0.41
     etcétera
    0.40
    ちなみに
    0.40
    並且
    0.38
    并在
    0.38
    0.38
     एक्चुअली
    0.38
    POSITIVE LOGITS
    ،
    1.66
    ,
    1.48
    ，
    1.42
    ፣
    1.35
     ،
    1.22
    ၊
    1.21
    ，“
    1.02
    ，《
    1.02
     ፣
    1.00
    $,
    0.95
    Activations Density 0.850%

    No Known Activations