© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 6542
    Prev
    Next
    INDEX
    Explanations

    comparing two things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
     unusual
    0.85
     unusually
    0.81
     buenas
    0.76
     ingenious
    0.76
     multilateral
    0.75
    运气
    0.75
    下一步
    0.75
     吉
    0.74
     expansive
    0.74
    fulfilled
    0.73
    POSITIVE LOGITS
     difference
    2.19
     differences
    2.19
    Difference
    2.17
     comparison
    2.13
     Difference
    2.13
    Differences
    2.12
     Comparison
    2.12
     Differences
    2.10
    Comparison
    2.05
     comparing
    2.02
    Activations Density 1.398%

    No Known Activations