© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40654
    Prev
    Next
    INDEX
    Explanations

    pressing future development

    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
    捕捉
    0.48
    negl
    0.47
    ان
    0.43
    ည်
    0.43
    شي
    0.41
    }}^{(
    0.41
    اق
    0.41
     hogares
    0.40
    ለት
    0.40
    dataloader
    0.40
    POSITIVE LOGITS
     პირადი
    0.45
     bot
    0.45
    ’:
    0.43
    obut
    0.42
     อย่าง
    0.41
    ONI
    0.41
    owali
    0.41
     바이
    0.41
    <start_of_image>
    0.40
     zmiany
    0.40
    Activations Density 0.002%

    No Known Activations