© 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. 31-GEMMASCOPE-2-RES-16K
    7. 14877
    Prev
    Next
    INDEX
    Explanations

    between

    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
     IRL
    0.57
     At
    0.56
     tide
    0.55
     Ecosystem
    0.55
     ~$
    0.55
     itch
    0.54
     macros
    0.53
    idia
    0.52
    顛
    0.52
    াব্য
    0.52
    POSITIVE LOGITS
    ErrorBoundary
    0.55
    Pam
    0.52
    幹
    0.52
    Spacer
    0.50
     ሁ
    0.49
     poitrine
    0.49
    ৃ
    0.48
    聞いて
    0.47
     কামাল
    0.47
    ྃ
    0.47
    Activations Density 0.003%

    No Known Activations