© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10605
    Prev
    Next
    INDEX
    Explanations

    computational chemistry

    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_16k_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
     ש
    0.54
    良い
    0.54
    驄
    0.49
    竑
    0.48
    Estos
    0.48
    Guinea
    0.47
     אבל
    0.46
     યાદ
    0.46
     સફેદ
    0.46
    Pero
    0.46
    POSITIVE LOGITS
    गण
    0.45
     sırasında
    0.44
     cenderung
    0.42
     экологи
    0.42
    bing
    0.41
    <em>
    0.40
    mu
    0.39
     rejuven
    0.39
    قة
    0.38
     cashier
    0.38
    Activations Density 0.058%

    No Known Activations