© 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. 44075
    Prev
    Next
    INDEX
    Explanations

    begin followed by code construct

    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
    т
    1.34
    د
    1.27
     it
    1.22
    д
    1.19
     you
    1.18
    ட்
    1.12
    你
    1.12
     améli
    1.10
    ي
    1.10
    ا
    1.09
    POSITIVE LOGITS
    dong
    0.88
    is
    0.87
    ↵
    0.84
    ine
    0.82
    r
    0.81
    ious
    0.79
    ,’”
    0.78
    lan
    0.77
    ac
    0.76
    ini
    0.75
    Activations Density 0.000%

    No Known Activations