© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13343
    Prev
    Next
    INDEX
    Explanations

    linking services, disdain for, Suzie's

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

    breaking of, explore alternatives, digital ease

    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_16k_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
    
    0.40
     Ter
    0.39
     E
    0.38
     
    0.37
     Rh
    0.37
    ähr
    0.35
     Redmond
    0.35
     Atatürk
    0.35
    ⁠
    0.35
    🎄
    0.35
    POSITIVE LOGITS
    確かに
    0.49
     mencionado
    0.47
    とのこと
    0.46
    indeed
    0.46
    presumably
    0.45
     indeed
    0.45
     mencion
    0.44
     mencionó
    0.44
    遁
    0.43
     언급
    0.43
    Activations Density 0.167%

    No Known Activations