© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167152
    Prev
    Next
    INDEX
    Explanations

    after mention or truly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    㭜
    0.41
    tgts
    0.39
    ⌄
    0.39
     सब्सक्राइब
    0.38
    ✽
    0.38
    chets
    0.37
    الج
    0.37
    \|_{
    0.36
    ARCHITECTURE
    0.36
    緣
    0.36
    POSITIVE LOGITS
     worried
    0.43
     cumulative
    0.42
     cron
    0.41
     familiar
    0.40
     chị
    0.40
     preced
    0.39
     anon
    0.39
     excited
    0.38
     sequential
    0.38
     jail
    0.38
    Activations Density 0.000%

    No Known Activations