© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7758
    Prev
    Next
    INDEX
    Explanations

    monument commemorating memorials remembrance

    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
    Not in Any Lists

    No Comments

    Negative Logits
     creatine
    0.71
     goodies
    0.70
     serotonin
    0.68
     critters
    0.67
     baddies
    0.63
     testosterone
    0.62
     endocr
    0.61
    뾰
    0.61
     infestations
    0.61
     infections
    0.60
    POSITIVE LOGITS
     memorial
    2.45
     commemoration
    2.27
     remembrance
    2.23
     memorials
    2.20
    纪念
    2.17
     commemorating
    2.17
     commemorate
    2.14
     commemorative
    2.13
     commemor
    2.09
    memorial
    2.03
    Activations Density 0.214%

    No Known Activations