© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4102
    Prev
    Next
    INDEX
    Explanations

    describes situation or evaluation

    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_12_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
    破坏
    1.07
    𝗗
    1.00
     tenho
    0.94
    保证
    0.92
    adhesive
    0.92
    办法
    0.91
    𝗸
    0.90
    𝗦
    0.89
    积极
    0.89
    𝗙
    0.88
    POSITIVE LOGITS
     mutually
    0.93
     decre
    0.76
     informa
    0.75
    راس
    0.75
     মহল
    0.75
     encom
    0.73
     decid
    0.73
     concord
    0.73
    دي
    0.73
     OMC
    0.72
    Activations Density 0.000%

    No Known Activations