© 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. 53-GEMMASCOPE-2-RES-262K
    7. 84112
    Prev
    Next
    INDEX
    Explanations

    listing requirements and problems

    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_53_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
    Ё
    0.44
    쉽
    0.41
     cev
    0.41
     제조
    0.40
    唰
    0.40
    긁
    0.39
     двигателя
    0.39
    Ṭ
    0.39
    舺
    0.39
    プラ
    0.38
    POSITIVE LOGITS
    billed
    0.44
    abbe
    0.39
    sprecher
    0.38
     pancake
    0.38
    bio
    0.38
     tired
    0.37
     weary
    0.37
     tide
    0.36
    పాద
    0.36
    惠
    0.36
    Activations Density 0.000%

    No Known Activations