© 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. 77926
    Prev
    Next
    INDEX
    Explanations

    dataframes and discussions

    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
     স্বর্ণ
    0.45
     tirelessly
    0.43
    প
    0.42
    ។
    0.42
     పూర్తిగా
    0.40
     এগুলো
    0.39
     repulsive
    0.39
     Tayler
    0.38
     bur
    0.38
     intensively
    0.38
    POSITIVE LOGITS
    )};
    0.50
     Articles
    0.46
    পালের
    0.45
     брак
    0.44
    附件
    0.43
    罹
    0.43
    凡
    0.43
     incol
    0.42
    0.42
     aos
    0.42
    Activations Density 0.006%

    No Known Activations