© 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-16K
    7. 13940
    Prev
    Next
    INDEX
    Explanations

    enabling users

    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_16k_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
    0.43
     serene
    0.39
     написа
    0.38
     :
    0.38
    </a>
    0.38
     very
    0.37
    jà
    0.37
     recente
    0.37
     generous
    0.37
     vå
    0.37
    POSITIVE LOGITS
    provides
    0.48
    riculum
    0.47
     proporcionan
    0.46
     proporciona
    0.45
    亥
    0.45
     পাকিস্তানিদের
    0.45
    Provides
    0.43
     таксама
    0.43
    证券公司
    0.43
     ሂደ
    0.43
    Activations Density 0.063%

    No Known Activations