© 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-262K
    7. 9085
    Prev
    Next
    INDEX
    Explanations

    distinct

    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_262k_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
     dearly
    1.79
    向け
    1.77
    َ
    1.70
     アップ
    1.68
    いて
    1.65
    ії
    1.64
    อีก
    1.63
    ਂ
    1.63
    रा
    1.60
    ので
    1.60
    POSITIVE LOGITS
    ни
    2.05
    amente
    1.72
    ાં
    1.70
    möglich
    1.65
    sville
    1.55
    ता
    1.53
     ràng
    1.52
     Strokes
    1.52
    ა
    1.52
    smanship
    1.51
    Activations Density 0.052%

    No Known Activations