© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212370
    Prev
    Next
    INDEX
    Explanations

    while, but, though

    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
     ثلاث
    0.40
     ucfirst
    0.40
     infile
    0.39
    knowing
    0.38
    橇
    0.37
    িষ্ট
    0.36
    晃
    0.36
     Mondays
    0.36
    蓬
    0.36
    ونس
    0.36
    POSITIVE LOGITS
    skill
    0.42
    ETE
    0.40
     tüm
    0.40
    Skill
    0.39
     bond
    0.38
    \<
    0.38
     übernommen
    0.37
    ㄱ
    0.37
     situazione
    0.36
    ibre
    0.36
    Activations Density 0.001%

    No Known Activations