© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10133
    Prev
    Next
    INDEX
    Explanations

    made of or from materials

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

    organized or built with

    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
     বিরোধিতা
    0.59
    議論
    0.57
     rapproche
    0.54
    指摘
    0.54
     함수의
    0.54
     eventuali
    0.52
     বুঝিতে
    0.52
    <unused48>
    0.52
    कांग्रेस
    0.52
     निर्ण
    0.51
    POSITIVE LOGITS
    精心
    0.85
     meticulously
    0.80
     thoughtfully
    0.76
     with
    0.76
     carefully
    0.75
     crafted
    0.70
     lovingly
    0.70
     handcrafted
    0.69
     meticulous
    0.68
     expertly
    0.68
    Activations Density 0.129%

    No Known Activations