© 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. 61783
    Prev
    Next
    INDEX
    Explanations

    whose feast, like a

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

    refusing inappropriate content

    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
    辯
    0.48
    pta
    0.46
    覺得
    0.44
    наче
    0.44
    మో
    0.44
    ዴ
    0.43
    मक
    0.42
    ت
    0.41
    tie
    0.41
    要在
    0.41
    POSITIVE LOGITS
     ตัว
    0.57
     ยาว
    0.57
     Букмекердик
    0.54
     น้ำ
    0.53
     กลุ่ม
    0.53
     ร้อย
    0.52
     ลักษณะ
    0.50
     görsel
    0.50
     天然
    0.49
     ကျ
    0.49
    Activations Density 0.000%

    No Known Activations