© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    O(log n)

    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
    রিষ্ঠ
    0.41
    匏
    0.38
     MERCHANTABILITY
    0.38
    慝
    0.37
     Dezember
    0.37
     жовтня
    0.37
     physi
    0.36
     $)$
    0.36
    leistung
    0.36
     ခု
    0.36
    POSITIVE LOGITS
    log
    0.66
     log
    0.64
    Log
    0.55
    logn
    0.53
     Log
    0.53
    linear
    0.51
    ilog
    0.47
     लॉग
    0.46
    logfile
    0.44
     logs
    0.44
    Activations Density 0.008%

    No Known Activations