© 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-65K
    7. 21053
    Prev
    Next
    INDEX
    Explanations

    listing and emphasizing

    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_65k_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
    Жен
    0.54
     companhia
    0.53
     chant
    0.50
    ﺭ
    0.48
    Chocolate
    0.47
    Conse
    0.47
    Labor
    0.47
    Memorial
    0.46
    Rent
    0.46
    પ
    0.46
    POSITIVE LOGITS
     Orient
    0.50
     Mark
    0.45
     आँ
    0.45
    comers
    0.45
     বছরে
    0.45
     ఇ
    0.44
    的一些
    0.44
    inių
    0.43
     நாளில்
    0.42
     Cov
    0.42
    Activations Density 0.011%

    No Known Activations