© 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. 113580
    Prev
    Next
    INDEX
    Explanations

    start of a sequence

    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
    Щ
    0.50
    ཧ
    0.46
    𝙊
    0.46
    Ր
    0.46
    ओवर
    0.45
    Código
    0.45
    oes
    0.45
    ري
    0.44
    緹
    0.44
    FUND
    0.43
    POSITIVE LOGITS
     καθ
    0.47
     கண
    0.47
    因为它
    0.45
     KMS
    0.44
     preempt
    0.43
     dilute
    0.43
    dry
    0.42
    عاد
    0.41
     благо
    0.40
     cleanly
    0.40
    Activations Density 0.003%

    No Known Activations