© 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. 134068
    Prev
    Next
    INDEX
    Explanations

    public opinion and disgust

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

    advertisement content and copy

    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
    但是在
    0.49
     సంవత్స
    0.45
    ⱼ
    0.44
    業務
    0.42
    ังก์ชัน
    0.41
    꼫
    0.41
    <unused2148>
    0.41
    眹
    0.41
     कर्मचारी
    0.40
    อยู่ใน
    0.40
    POSITIVE LOGITS
    comedy
    0.52
     menonton
    0.46
     نفرت
    0.46
     රස
    0.44
     amusing
    0.44
     হাস্য
    0.44
     disgusting
    0.43
    curr
    0.43
     pebbles
    0.43
     spray
    0.43
    Activations Density 0.000%

    No Known Activations