© 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. 145479
    Prev
    Next
    INDEX
    Explanations

    predicting common word pairings

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

    apply online

    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
     Pří
    0.45
    ：
    0.44
    裡的
    0.43
    可以看到
    0.41
    💸
    0.40
    ￡
    0.39
     👋
    0.39
    ➘
    0.38
    ❌
    0.38
    副作用
    0.38
    POSITIVE LOGITS
     ஒன்றாகும்
    0.44
     registration
    0.44
     bert
    0.43
     Mustafa
    0.42
    טו
    0.41
     आगामी
    0.41
     ముందు
    0.41
     Demir
    0.40
     LSP
    0.40
     preparedness
    0.39
    Activations Density 0.001%

    No Known Activations