© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 32872
    Prev
    Next
    INDEX
    Explanations

    Wittgenstein, resistant MRSA, RLHF

    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_16_width_262k_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
    st
    0.55
    谯
    0.55
    in
    0.54
     الجهاز
    0.54
    name
    0.53
    (
    0.53
    绩
    0.52
    recording
    0.52
     والخ
    0.52
    مق
    0.51
    POSITIVE LOGITS
     zwei
    0.62
     $
    0.61
     sechs
    0.61
     với
    0.59
     $\$
    0.58
     giới
    0.57
    㶲
    0.57
     snowboarding
    0.57
    álních
    0.55
     दोन
    0.55
    Activations Density 0.022%

    No Known Activations