© 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. 44171
    Prev
    Next
    INDEX
    Explanations

    module.exports, export

    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
    D
    1.36
    R
    1.31
    ის
    1.26
    ют
    1.23
    みました
    1.20
     in
    1.19
    იდან
    1.17
    S
    1.16
    L
    1.16
     epigen
    1.15
    POSITIVE LOGITS
    こちら
    1.31
     waxaa
    1.30
    琍
    1.30
     liye
    1.26
    べく
    1.26
    ോധ
    1.24
    我们
    1.23
    autres
    1.20
    メント
    1.18
    να
    1.17
    Activations Density 0.001%

    No Known Activations