© 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. 36053
    Prev
    Next
    INDEX
    Explanations

    drop shipped, never know, a great

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

    unethical cannibalism

    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
    ហ
    0.48
    晖
    0.48
    ។
    0.45
    领域
    0.45
    Authorize
    0.45
    领域的
    0.45
    摩托
    0.44
    Emit
    0.43
    别的
    0.43
     அமைச்ச
    0.43
    POSITIVE LOGITS
     国産
    0.48
    poem
    0.47
     nonché
    0.47
     रोजिक
    0.46
    stakes
    0.46
     nový
    0.46
     tapa
    0.45
    
    0.45
     Thanksgiving
    0.45
     Baru
    0.44
    Activations Density 0.000%

    No Known Activations