© 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. 100118
    Prev
    Next
    INDEX
    Explanations

    filled with

    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
    intensité
    0.40
    elés
    0.40
    伖
    0.40
     উৎপত্তি
    0.37
     限
    0.37
    usen
    0.37
     স্বেচ্ছ
    0.36
    appropri
    0.36
     appealing
    0.35
     бес
    0.35
    POSITIVE LOGITS
     ഔ
    0.46
    ният
    0.41
     RARRAY
    0.40
    лье
    0.39
     Atha
    0.38
    कीय
    0.38
     dakkh
    0.38
     Kull
    0.37
    луу
    0.37
     monks
    0.37
    Activations Density 0.000%

    No Known Activations