© 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. 30541
    Prev
    Next
    INDEX
    Explanations

    kotlin lateinit declarations, json, yaml

    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
    ק
    0.59
     authorize
    0.58
     pollute
    0.55
     appear
    0.54
    க
    0.54
    ｶ
    0.54
    ти
    0.54
     organize
    0.54
     هیڅ
    0.53
    ک
    0.52
    POSITIVE LOGITS
    是對
    0.59
    iffs
    0.57
    ਰ
    0.56
    ild
    0.53
    amped
    0.53
    ihin
    0.53
     manglid
    0.53
    ώ
    0.53
     tentang
    0.52
     जुगा
    0.51
    Activations Density 0.000%

    No Known Activations