© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 47669
    Prev
    Next
    INDEX
    Explanations

    ground truth or labels

    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
     stehen
    0.55
    这样
    0.52
     souvent
    0.51
    urro
    0.50
    现在
    0.50
     هناك
    0.50
     overwhelmingly
    0.49
    㖩
    0.49
     utan
    0.49
     undercut
    0.49
    POSITIVE LOGITS
    Pins
    0.55
    ज्ञात
    0.54
    nour
    0.52
    nore
    0.52
     idP
    0.50
    ною
    0.50
    Noir
    0.48
    AOrdenar
    0.47
    ‌آ
    0.47
    periods
    0.47
    Activations Density 0.017%

    No Known Activations