© 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. 128049
    Prev
    Next
    INDEX
    Explanations

    anniversary in September

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

    budget cuts

    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
     者
    0.54
     verwend
    0.50
    憊
    0.50
     اسم
    0.48
     احتم
    0.47
    COLORS
    0.46
     матеріа
    0.46
     numele
    0.46
     منف
    0.45
     αποτε
    0.44
    POSITIVE LOGITS
    시아
    0.45
    등학교
    0.45
    。
    0.44
    بی
    0.44
    ండో
    0.42
     cheerio
    0.42
    택
    0.42
     stratified
    0.42
    سازی
    0.42
     hospitable
    0.42
    Activations Density 0.001%

    No Known Activations