© 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. 164985
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    cocktail making concepts

    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
    荊
    0.47
    改正
    0.45
    两
    0.44
    ungnya
    0.42
     цьому
    0.42
     상당
    0.42
    上
    0.42
     공개
    0.42
     этого
    0.42
     이전
    0.42
    POSITIVE LOGITS
     Businesses
    0.52
     Florida
    0.48
    ằng
    0.46
    éz
    0.46
    ρέ
    0.46
     Australia
    0.45
     Novels
    0.44
    lád
    0.44
     Airlines
    0.43
     Microsc
    0.43
    Activations Density 0.002%

    No Known Activations