© 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. 168575
    Prev
    Next
    INDEX
    Explanations

    various followed by methods

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

    handling edge cases

    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
     وړ
    0.46
    สูงสุด
    0.45
    ड़ों
    0.43
     `<=`
    0.43
    स्थ
    0.42
    不了
    0.41
     marché
    0.39
    jumpa
    0.39
     ajust
    0.39
    ړو
    0.39
    POSITIVE LOGITS
    akanan
    0.48
     murmur
    0.46
    ational
    0.46
     exemplar
    0.46
    s
    0.46
     今日
    0.46
     Bedürfn
    0.45
     เพิ่ม
    0.44
     Chris
    0.44
    hetical
    0.44
    Activations Density 0.000%

    No Known Activations