© 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. 31-GEMMASCOPE-2-RES-262K
    7. 56944
    Prev
    Next
    INDEX
    Explanations

    generate lists and stories

    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_31_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
    ت
    0.57
    ال
    0.55
    are
    0.50
    s
    0.48
    ᆫ
    0.46
    sop
    0.44
    、
    0.43
    ܣ
    0.42
    ا
    0.42
    screens
    0.41
    POSITIVE LOGITS
    PerTrial
    0.49
    ക്കുന്നത്
    0.45
    ूक
    0.44
     машиналары
    0.44
     Cessna
    0.42
    ंसारी
    0.42
     Repe
    0.41
     previously
    0.41
    ={()
    0.41
     Çalış
    0.41
    Activations Density 0.009%

    No Known Activations