© 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. 143225
    Prev
    Next
    INDEX
    Explanations

    based on surveys conducted

    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
     metaphorical
    0.41
     стоимость
    0.39
     исход
    0.39
     фаса
    0.39
     sắc
    0.38
     BOS
    0.37
    </strong>
    0.37
    </sup>
    0.37
     간
    0.37
     '${
    0.37
    POSITIVE LOGITS
    ak
    0.66
    ade
    0.54
     sera
    0.54
    abe
    0.52
    kami
    0.52
    achi
    0.52
    kde
    0.52
    itats
    0.52
    ua
    0.51
    que
    0.50
    Activations Density 0.002%

    No Known Activations