© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 138546
    Prev
    Next
    INDEX
    Explanations

    fandom wikis

    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
    usz
    0.53
     about
    0.50
    ↵↵
    0.49
    usr
    0.48
     sustaining
    0.46
    枝
    0.46
     cycling
    0.46
    читься
    0.46
     Can
    0.46
     hör
    0.46
    POSITIVE LOGITS
    imbang
    0.52
    thrombin
    0.52
    ды
    0.51
    дает
    0.51
    𝟏
    0.51
    imbangkan
    0.49
     xuất
    0.49
    rate
    0.48
    ”،
    0.47
     hiệu
    0.47
    Activations Density 0.000%

    No Known Activations