© 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. 85992
    Prev
    Next
    INDEX
    Explanations

    legal or business actions and changes

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

    finding within report due

    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
    琭
    0.55
     ফিল্ম
    0.52
     टें
    0.49
    หลากหลาย
    0.49
     অসংখ্য
    0.48
    مثل
    0.48
    小组
    0.48
    परिवार
    0.48
     जैसे
    0.47
    ’;
    0.47
    POSITIVE LOGITS
     ecol
    0.51
     evi
    0.51
     Tagen
    0.51
    ك
    0.49
     ej
    0.49
     éta
    0.49
     daß
    0.48
     koe
    0.47
    s
    0.47
     obser
    0.46
    Activations Density 0.001%

    No Known Activations