© 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. 5788
    Prev
    Next
    INDEX
    Explanations

    best answer

    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
     stems
    0.58
    寶
    0.54
    题材
    0.54
     tý
    0.53
    nP
    0.53
     oligonucle
    0.52
    omenclature
    0.51
    amide
    0.50
     vraag
    0.50
    OMET
    0.49
    POSITIVE LOGITS
    ఖా
    0.55
    ڡ
    0.50
     Patient
    0.50
     blade
    0.49
     Maintenance
    0.49
     object
    0.48
     explanation
    0.48
     特許庁
    0.48
     Soldier
    0.47
     أ
    0.47
    Activations Density 0.000%

    No Known Activations