© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6562
    Prev
    Next
    INDEX
    Explanations

    bad or negative outcomes

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

    big bad

    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_53_width_65k_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
    вена
    0.35
    ⵡ
    0.35
     সঞ্জীবনী
    0.35
     неви
    0.34
    angga
    0.33
     நிர
    0.33
    匏
    0.33
    ዴ
    0.32
     הו
    0.32
     প্রহ
    0.32
    POSITIVE LOGITS
     bad
    4.78
    bad
    4.38
     Bad
    4.34
    Bad
    4.34
     BAD
    4.19
    BAD
    3.98
    坏
    3.59
     بد
    3.39
    壞
    3.20
    悪い
    3.09
    Activations Density 0.233%

    No Known Activations