© 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. 4216
    Prev
    Next
    INDEX
    Explanations

    health concerns or before making decisions

    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
    Attorney
    0.47
     attorney
    0.47
     berpeng
    0.44
    퐫
    0.43
     corrobor
    0.42
    이
    0.42
    律师
    0.40
     rapporti
    0.40
    Executive
    0.39
    ೂ
    0.39
    POSITIVE LOGITS
     Incluso
    0.44
     abandon
    0.43
     abandoning
    0.43
     consuming
    0.40
     Abandon
    0.40
     debilit
    0.39
     aband
    0.39
    พวกเขา
    0.38
     yeah
    0.38
     newborns
    0.38
    Activations Density 0.059%

    No Known Activations