© 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. 53366
    Prev
    Next
    INDEX
    Explanations

    more than one

    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
    ouncing
    0.41
    elah
    0.40
     اکنون
    0.39
    <0xB9>
    0.38
     пенсии
    0.38
     এখন
    0.38
     औसत
    0.37
    hyth
    0.37
     demasi
    0.36
    ineries
    0.36
    POSITIVE LOGITS
    嘉
    0.39
    Knife
    0.37
    وو
    0.37
     hoş
    0.36
    Machine
    0.36
     supuesto
    0.36
     paintbrush
    0.35
     も
    0.35
     clipboard
    0.35
     purely
    0.34
    Activations Density 0.001%

    No Known Activations