© 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. 8575
    Prev
    Next
    INDEX
    Explanations

    editing or inserting content

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

    customizing specific outcomes

    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
     counsels
    0.40
     theology
    0.39
     nobis
    0.39
     тща
    0.38
     мла
    0.38
     ಚುನ
    0.37
     creencias
    0.37
    惶
    0.36
    犢
    0.36
     miseric
    0.36
    POSITIVE LOGITS
     automatically
    0.55
     using
    0.55
    嵌套
    0.55
    自定义
    0.54
     Using
    0.52
     Android
    0.51
     Excel
    0.51
    自动
    0.50
     menggunakan
    0.50
    多个
    0.50
    Activations Density 0.159%

    No Known Activations