© 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. 142731
    Prev
    Next
    INDEX
    Explanations

    bucket, python, form, todo, analysis, image, parser, route, item, include

    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
    \
    0.94
    न्त्री
    0.82
     یک
    0.78
     وقتی
    0.75
     یه
    0.74
     atriz
    0.73
    "
    0.72
     cnpj
    0.72
    titulo
    0.71
    ъ
    0.71
    POSITIVE LOGITS
    um
    0.96
    -
    0.86
    et
    0.76
    和其他
    0.68
    ou
    0.67
    之旅
    0.64
    高
    0.64
    ab
    0.64
     risk
    0.64
    ungs
    0.64
    Activations Density 0.042%

    No Known Activations