© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4836
    Prev
    Next
    INDEX
    Explanations

    should not or be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     sẽ
    1.11
     elucidation
    1.09
     uncharted
    1.09
     will
    1.06
     metabolic
    1.06
     phá
    1.05
    ó
    1.05
    ophageal
    1.02
     imprison
    0.99
     trophic
    0.99
    POSITIVE LOGITS
     helst
    1.48
    有的
    1.46
    Ideally
    1.43
    equal
    1.34
    ered
    1.33
    ात
    1.30
    eh
    1.30
     Ideally
    1.28
    臾
    1.26
    Be
    1.25
    Activations Density 0.140%

    No Known Activations