© 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. 14638
    Prev
    Next
    INDEX
    Explanations

    table headers

    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
    𝗴
    1.91
    ли
    1.86
    து
    1.74
    𝐞
    1.74
    𝗹
    1.72
    d
    1.70
    age
    1.70
    いた
    1.66
    isiert
    1.64
    ATION
    1.63
    POSITIVE LOGITS
    来说
    1.52
    ━━━━━━━━
    1.48
    ድግዳ
    1.40
    此之外
    1.39
     housekeeping
    1.34
     Loài
    1.34
     anchoring
    1.34
     vẻ
    1.31
     stipulated
    1.31
     hủy
    1.31
    Activations Density 0.007%

    No Known Activations