© 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. 28827
    Prev
    Next
    INDEX
    Explanations

    `+` or `*` after variables

    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
     vix
    0.48
     lights
    0.44
     Rosemary
    0.43
    мя
    0.42
     antimicrobial
    0.42
     руку
    0.41
     Ripp
    0.40
     可
    0.40
     rins
    0.40
     Lights
    0.40
    POSITIVE LOGITS
     solely
    0.42
     gratuito
    0.41
    tema
    0.39
    balik
    0.39
    シート
    0.39
    Aku
    0.38
     konflikt
    0.38
    ۔
    0.38
    예요
    0.38
    ۱۹
    0.38
    Activations Density 0.002%

    No Known Activations