© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 402
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
    ျေး
    0.56
    proving
    0.54
     دهند
    0.52
    ්‍
    0.52
    gast
    0.52
    -'].
    0.51
     Combat
    0.51
    鳟
    0.51
     প্রকাশক
    0.50
     देतात
    0.50
    POSITIVE LOGITS
     ouvert
    0.66
     go
    0.65
     went
    0.64
     open
    0.63
     head
    0.60
     put
    0.57
     otw
    0.57
     plan
    0.57
     Open
    0.54
     opened
    0.54
    Activations Density 2.021%

    No Known Activations