© 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. 210013
    Prev
    Next
    INDEX
    Explanations

    supplied, complete, article, case, malicious

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

    loss and minimize

    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
    ativa
    0.47
    ன்கள்
    0.46
    ibilit
    0.46
     pajamas
    0.46
    生产
    0.45
    aliment
    0.44
    𝕖
    0.44
     mortal
    0.43
     listo
    0.43
     favor
    0.43
    POSITIVE LOGITS
     نتیجه
    0.49
    طبق
    0.47
     وزارت
    0.45
     ';
    0.45
    usepackage
    0.45
     عباس
    0.45
    xcsche
    0.44
     altres
    0.44
     }),
    0.43
     були
    0.42
    Activations Density 0.001%

    No Known Activations