© 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. 16-GEMMASCOPE-2-RES-262K
    7. 20973
    Prev
    Next
    INDEX
    Explanations

    non-English words and code constructs

    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_16_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
    <0x8F>
    0.57
    ні
    0.56
     nipple
    0.55
     squadrons
    0.55
     venues
    0.52
     vowels
    0.52
     axles
    0.52
     menace
    0.52
     outlay
    0.52
     indemnity
    0.51
    POSITIVE LOGITS
    ኩ
    0.52
    ご注文
    0.51
    ৩২
    0.51
    ৬
    0.51
    友達
    0.50
    我是
    0.49
    kinetic
    0.49
     ஹெ
    0.49
    ifiz
    0.48
    oelect
    0.47
    Activations Density 0.000%

    No Known Activations