© 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. 212098
    Prev
    Next
    INDEX
    Explanations

    wⱼ subscript

    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
    inputFields
    0.39
    0.39
     chic
    0.37
     squares
    0.37
     olay
    0.36
     द
    0.36
     sneaky
    0.36
     fut
    0.35
     דו
    0.35
     bolster
    0.35
    POSITIVE LOGITS
    ところ
    0.40
     penduduk
    0.38
     கடி
    0.38
    挺
    0.38
    れて
    0.38
    विधा
    0.37
    повід
    0.37
    ಲೋ
    0.37
     proté
    0.37
    鎳
    0.36
    Activations Density 0.000%

    No Known Activations