© 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. 156085
    Prev
    Next
    INDEX
    Explanations

    Portuguese, canal, scan, marry, purchased

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

    transliteration and greetings

    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
    短短
    0.55
    ஞ
    0.47
    marginLeft
    0.46
     તેમના
    0.45
    虽
    0.44
    引领
    0.44
     таъ
    0.43
    ządz
    0.43
    四周
    0.42
     совсем
    0.42
    POSITIVE LOGITS
    𝗵
    0.46
     purifying
    0.46
     prepping
    0.46
     bersih
    0.45
    雛
    0.45
     čist
    0.44
     세
    0.41
     हाय
    0.40
    轉換
    0.40
     제외
    0.40
    Activations Density 0.000%

    No Known Activations