© 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. 83775
    Prev
    Next
    INDEX
    Explanations

    solar panel

    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
    匏
    0.55
    Ceylon
    0.48
     ย
    0.47
    教师
    0.46
    ification
    0.46
    LAYOUT
    0.43
     devez
    0.43
    rapers
    0.43
    ه
    0.43
    گ
    0.42
    POSITIVE LOGITS
     consist
    0.47
     vida
    0.45
    sock
    0.45
     sozinha
    0.43
     necessariamente
    0.42
     conden
    0.41
     renovación
    0.41
     necessarily
    0.40
     necesariamente
    0.40
    ভাবে
    0.39
    Activations Density 0.003%

    No Known Activations