© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9901
    Prev
    Next
    INDEX
    Explanations

    Amos Yee

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

    words starting with Am

    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_40_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
    燹
    0.43
    äst
    0.41
    แตกต่าง
    0.39
    ský
    0.38
    க்கப்பட்டுள்ளது
    0.38
    杽
    0.38
    erdas
    0.38
    ৯
    0.38
    ming
    0.37
    nya
    0.36
    POSITIVE LOGITS
     Am
    1.08
    Am
    1.08
     ам
    0.99
     Ам
    0.96
     AM
    0.85
     অ্যাম
    0.81
     am
    0.80
     Amir
    0.77
     Amr
    0.76
     Amelia
    0.73
    Activations Density 0.128%

    No Known Activations