© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9310
    Prev
    Next
    INDEX
    Explanations

    Dev, Tech, Prep, SEP

    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
    ação
    2.23
    тная
    2.22
    ЛИ
    2.20
    ﻢ
    2.16
    тное
    2.08
    oft
    2.03
    ۰۰
    2.00
    ㎜
    1.94
    IRIS
    1.93
    하기
    1.88
    POSITIVE LOGITS
    на
    2.38
    u
    2.23
    न
    2.23
    كين
    2.13
    ك
    2.08
    م
    1.91
     notificações
    1.88
    ج
    1.85
    麼
    1.79
    くちゃ
    1.74
    Activations Density 0.232%

    No Known Activations