© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 155368
    Prev
    Next
    INDEX
    Explanations

    academic degrees and qualifications

    np_acts-logits-general · gemini-2.5-flash-lite

    introducing First Customer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    岳
    0.45
     قبض
    0.44
    blest
    0.43
    calorie
    0.42
     forState
    0.42
    dueDate
    0.42
     মূল্য
    0.41
     شغل
    0.41
     বিষয়ক
    0.41
     মামলায়
    0.40
    POSITIVE LOGITS
    كي
    0.53
     performans
    0.52
     (-\
    0.49
     talvez
    0.48
    জ
    0.48
     പ്രതിഷേധ
    0.48
    വ്ര
    0.48
     pelas
    0.48
     diplom
    0.47
     comis
    0.47
    Activations Density 0.000%

    No Known Activations