© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 144284
    Prev
    Next
    INDEX
    Explanations

    filter out

    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
    и
    0.62
    ներ
    0.59
    ی
    0.58
    lle
    0.56
    е
    0.54
    не
    0.53
    ين
    0.53
    ته
    0.53
    ву
    0.52
    한
    0.52
    POSITIVE LOGITS
     filters
    1.49
     Filters
    1.41
     filtering
    1.38
    filters
    1.37
    filter
    1.35
    Filter
    1.35
    filtering
    1.32
    Filters
    1.31
     Filter
    1.30
     filtr
    1.30
    Activations Density 0.028%

    No Known Activations