© 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. 109076
    Prev
    Next
    INDEX
    Explanations

    answers to review questions

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

    freedom, not price

    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
    娇
    0.50
    运动员
    0.49
    ভো
    0.47
    种子
    0.47
    Что
    0.47
    罗斯
    0.46
    Есть
    0.46
    ઢ
    0.46
    Влади
    0.46
    렀
    0.46
    POSITIVE LOGITS
    Biz
    0.48
     /
    0.47
     reference
    0.47
     कारोबार
    0.46
    ners
    0.45
     auditorium
    0.44
     headroom
    0.44
    insa
    0.44
    own
    0.44
    markets
    0.43
    Activations Density 0.001%

    No Known Activations