© 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. 172802
    Prev
    Next
    INDEX
    Explanations

    laptops and Asus

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

    movement and capacity

    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
     я
    0.46
    ]='
    0.46
    ]=
    0.44
    ]=='
    0.44
     realty
    0.42
     govern
    0.41
    ']=
    0.41
     ولی
    0.40
    ሉት
    0.40
    =}
    0.40
    POSITIVE LOGITS
     ASU
    0.44
     inhal
    0.42
     aromatherapy
    0.42
     breastfeeding
    0.42
     gravid
    0.41
    උ
    0.41
     kuliah
    0.41
     trening
    0.41
     Suche
    0.40
     alasan
    0.40
    Activations Density 0.001%

    No Known Activations