© 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-65K
    7. 27098
    Prev
    Next
    INDEX
    Explanations

    OH MY GOD

    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_65k_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
    स्ट
    0.41
    𝚕
    0.41
    ችል
    0.41
    ப்பையும்
    0.40
     montón
    0.38
    ച്ച
    0.38
    盛
    0.38
    𝚃
    0.38
    𝖑
    0.38
    об
    0.37
    POSITIVE LOGITS
     Counc
    0.42
     exclusives
    0.39
     Pelicans
    0.39
     Yes
    0.38
     Collaboration
    0.38
     enquiries
    0.38
     Parole
    0.38
    yana
    0.38
     Calculus
    0.37
     никаких
    0.37
    Activations Density 0.004%

    No Known Activations