© 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-262K
    7. 138375
    Prev
    Next
    INDEX
    Explanations

    rights, citizen, native

    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
    xi
    0.51
    supportsFocus
    0.50
    t
    0.50
     quadrada
    0.49
     নরম
    0.46
    POSIX
    0.46
    ти
    0.46
    _{+}
    0.46
    CLUS
    0.45
     paru
    0.44
    POSITIVE LOGITS
     leid
    0.41
    urned
    0.41
     Threads
    0.41
    岄
    0.41
    름
    0.39
     ისინი
    0.38
    iking
    0.38
     приходится
    0.37
     ट्रोल
    0.37
     Browse
    0.37
    Activations Density 0.005%

    No Known Activations