© 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. 24-GEMMASCOPE-2-RES-262K
    7. 1982
    Prev
    Next
    INDEX
    Explanations

    codes

    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_24_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
     OCLC
    0.37
     galactose
    0.37
     v
    0.36
     LEED
    0.35
    
    0.35
     prise
    0.34
    사랑
    0.33
     DDT
    0.32
    룔
    0.32
     PKC
    0.32
    POSITIVE LOGITS
    ର୍
    0.37
     เช่น
    0.35
    ﻨ
    0.33
     軽量
    0.31
    Un
    0.31
     обеспечить
    0.29
     grundsätzlich
    0.29
    Ar
    0.29
    していますが
    0.29
     শুক্রবার
    0.29
    Activations Density 0.002%

    No Known Activations