© 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. 126492
    Prev
    Next
    INDEX
    Explanations

    legal, business, and technical contexts

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

    struggle, receives, praise

    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
     ऑफ
    0.58
    স্ট্র
    0.52
    是非常
    0.50
    怪物
    0.49
    好多
    0.47
     jednocześnie
    0.47
    类
    0.46
    同时也
    0.46
    大胆
    0.46
    也非常
    0.46
    POSITIVE LOGITS
     மணிய
    0.52
     praise
    0.46
    ৩১
    0.44
     Ambedkar
    0.44
     प्राप्ति
    0.43
     inherit
    0.43
     ORIG
    0.43
    ('/')
    0.43
    -__
    0.43
     শাসনের
    0.43
    Activations Density 0.000%

    No Known Activations