© 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. 145752
    Prev
    Next
    INDEX
    Explanations

    found by, passed by, itself

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

    Led by leaders

    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
     რა
    0.52
     MgII
    0.50
     她
    0.49
     মোত
    0.49
    劷
    0.48
     ইলেক্ট্রোলাই
    0.48
     appartement
    0.47
     ಮು
    0.46
     ဒီ
    0.46
     للد
    0.46
    POSITIVE LOGITS
    ザ
    0.47
    ת
    0.46
    olon
    0.45
    現場
    0.44
    یل
    0.43
    Источник
    0.43
     calling
    0.42
    声を
    0.42
    calling
    0.41
    ფერ
    0.41
    Activations Density 0.001%

    No Known Activations