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

    Neuronpedia

    Jacobian LensNEW
    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. 5086
    Prev
    Next
    INDEX
    Explanations

    concerns and requirements

    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
    牫
    0.23
    ivating
    0.23
    ographical
    0.23
    ルの
    0.22
    겠지만
    0.22
    atlantic
    0.22
     of
    0.22
    asting
    0.21
    Page
    0.21
    -)
    0.21
    POSITIVE LOGITS
     intensa
    0.28
     tại
    0.27
     ভুগ
    0.27
     famosos
    0.27
     және
    0.27
     extraordinaire
    0.27
     Klav
    0.27
     również
    0.26
     famosa
    0.26
     cũng
    0.26
    Activations Density 1.114%

    No Known Activations