© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 4849
    Prev
    Next
    INDEX
    Explanations

    introducing or explaining with analogy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
    т
    0.91
     सिद्धांतों
    0.87
     सिद्धांत
    0.86
    汇总
    0.86
    Authenticated
    0.84
    lN
    0.84
    োস
    0.83
     summarizes
    0.81
    クリ
    0.80
    л
    0.80
    POSITIVE LOGITS
     analogy
    1.26
     analogies
    0.87
    喩
    0.86
    喻
    0.86
     pain
    0.85
     painful
    0.78
     comparing
    0.78
     celery
    0.78
     comparator
    0.76
    quat
    0.76
    Activations Density 0.038%

    No Known Activations