© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163872
    Prev
    Next
    INDEX
    Explanations

    image source metadata

    np_acts-logits-general · gemini-2.5-flash-lite

    multi-lingual character sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Curr
    0.49
    鎂
    0.47
     Killed
    0.45
     Collected
    0.45
                
    0.44
     soins
    0.44
     Issued
    0.44
     Succeed
    0.44
     Headline
    0.44
    Lon
    0.43
    POSITIVE LOGITS
    ńskiej
    0.52
    长时间
    0.50
    ńska
    0.49
    ługa
    0.49
    قة
    0.48
    训
    0.48
    পাতি
    0.48
    ździer
    0.47
    ú
    0.47
    阁
    0.47
    Activations Density 0.001%

    No Known Activations