© 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. 99997
    Prev
    Next
    INDEX
    Explanations

    email, python, javascript, Outlook, box

    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
    ా
    0.45
    า
    0.44
    никами
    0.43
    apal
    0.42
    liefer
    0.41
    daw
    0.41
    ्स
    0.41
     tomo
    0.41
    nova
    0.40
    ா
    0.40
    POSITIVE LOGITS
    ١
    0.55
    ની
    0.49
     n
    0.47
    의
    0.44
    的
    0.44
     onClick
    0.43
     സോഷ്യ
    0.42
     hush
    0.42
    社會
    0.41
     watercolor
    0.41
    Activations Density 0.002%

    No Known Activations