© 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. 31-GEMMASCOPE-2-RES-262K
    7. 41342
    Prev
    Next
    INDEX
    Explanations

    documents and files

    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_31_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
    вом
    0.51
    مم
    0.47
    经济
    0.46
    مو
    0.46
     अर्थव्यवस्था
    0.45
    მდეგ
    0.45
    𝘴
    0.44
    [,,"
    0.43
    вими
    0.43
    ्यूशन
    0.42
    POSITIVE LOGITS
    ॥
    0.50
    の状態
    0.47
     palabra
    0.46
     לפני
    0.43
     nou
    0.42
    장은
    0.42
    ety
    0.41
    িতেছি
    0.41
     surprised
    0.41
    の設定
    0.41
    Activations Density 0.000%

    No Known Activations