© 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-65K
    7. 435
    Prev
    Next
    INDEX
    Explanations

    large language

    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_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
    in
    0.58
    li
    0.54
    lik
    0.50
    ieg
    0.49
    eli
    0.49
    -
    0.45
    ett
    0.45
    iek
    0.45
    lin
    0.44
    mo
    0.44
    POSITIVE LOGITS
    ות
    0.77
    ون
    0.61
     jazy
    0.61
    ור
    0.59
    有可能
    0.58
     language
    0.57
    ８
    0.54
     bahasa
    0.52
     Bahasa
    0.52
    )。
    0.52
    Activations Density 1.518%

    No Known Activations