© 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. 31-GEMMASCOPE-2-RES-262K
    7. 202827
    Prev
    Next
    INDEX
    Explanations

    describing features and regions

    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_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
    с
    0.55
    ы
    0.54
     измерения
    0.52
    ну
    0.47
     Пара
    0.45
    из
    0.44
    вает
    0.44
     объекта
    0.44
    ъ
    0.43
    㑯
    0.43
    POSITIVE LOGITS
     survival
    0.45
     bonuses
    0.44
     recirculation
    0.43
     Portugal
    0.42
     adju
    0.42
     acho
    0.41
     advanced
    0.41
     snowflakes
    0.41
     chunks
    0.41
     slogans
    0.41
    Activations Density 0.002%

    No Known Activations