© 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. 14237
    Prev
    Next
    INDEX
    Explanations

    independent nonprofit

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

    consult with

    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
    Software
    0.37
    科技有限公司
    0.33
     softwares
    0.33
    HTML
    0.33
    Permission
    0.33
    诛
    0.32
     unless
    0.32
     Software
    0.32
    本文
    0.32
    性质
    0.32
    POSITIVE LOGITS
    緍
    0.39
     腰
    0.39
    婦
    0.39
     halibut
    0.38
    齡
    0.38
     marijuana
    0.37
     വയ
    0.37
    monary
    0.36
     pregnancy
    0.36
    頸
    0.36
    Activations Density 0.287%

    No Known Activations