© 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. 127969
    Prev
    Next
    INDEX
    Explanations

    managing memory

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

    describing something artificial and serving

    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
     verkrij
    0.43
     hierv
    0.42
    +}(
    0.41
     männ
    0.41
     estimular
    0.41
    문에
    0.40
     képes
    0.40
     encontrará
    0.40
     அளவுக்கு
    0.39
     testis
    0.39
    POSITIVE LOGITS
     शरण
    0.52
    बिट
    0.48
     मिट
    0.45
    ꒷
    0.45
    fahrt
    0.44
     कब्रिस्तान
    0.43
     চেপে
    0.41
     ฟ้า
    0.40
    गोलिक
    0.40
    plist
    0.40
    Activations Density 0.002%

    No Known Activations