© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5561
    Prev
    Next
    INDEX
    Explanations

    multiplication, implementation, optimization

    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
    ión
    0.92
    د
    0.88
    માં
    0.85
    ના
    0.83
    在
    0.80
    ことを
    0.78
    就
    0.78
    ългария
    0.76
    我
    0.76
    的な
    0.75
    POSITIVE LOGITS
    is
    1.31
    n
    1.24
    ר
    1.20
    т
    1.17
    x
    1.16
    ت
    1.14
    ти
    1.13
    tr
    1.11
    ле
    1.09
    us
    1.07
    Activations Density 1.781%

    No Known Activations