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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 41-GEMMASCOPE-2-RES-16K
    7. 420
    Prev
    Next
    INDEX
    Explanations

    moving or holding objects

    np_max-act-logits · gemini-2.5-flash-lite

    objects and time

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
     fim
    0.36
     TMN
    0.36
     follicle
    0.35
     legume
    0.35
     $*$-
    0.35
     timeframe
    0.34
     seashell
    0.34
     corne
    0.33
     seter
    0.33
     schizophren
    0.33
    POSITIVE LOGITS
    ↵
    0.29
     അദ്ദേഹ
    0.29
    Updated
    0.29
    angular
    0.26
    antung
    0.26
    ank
    0.26
     chuckled
    0.26
     가격
    0.25
     उत्ते
    0.25
     привет
    0.25
    Activations Density 0.001%

    No Known Activations