© 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. 6868
    Prev
    Next
    INDEX
    Explanations

    counting or contextualizing phrases

    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
     vielfält
    0.29
     कठिना
    0.29
    嬸
    0.28
    示例
    0.27
    １
    0.27
     وال
    0.27
     ý
    0.27
    <0xD9>
    0.26
     उपयोगी
    0.26
     disa
    0.26
    POSITIVE LOGITS
     pós
    0.29
     WITH
    0.29
     BECAUSE
    0.29
    即便
    0.29
     THESE
    0.27
     EVEN
    0.27
     शुद्ध
    0.26
     post
    0.25
     excised
    0.25
     vaccinated
    0.25
    Activations Density 0.424%

    No Known Activations