© 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. 149639
    Prev
    Next
    INDEX
    Explanations

    Turkey conducted, controls the, dog in

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

    fee policies and penalties

    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
    有一个
    0.53
     большей
    0.50
    不是
    0.49
    toHave
    0.47
    すごく
    0.46
     ,\
    0.45
    新た
    0.45
    苎
    0.45
    startswith
    0.45
     wchar
    0.45
    POSITIVE LOGITS
    ↵
    0.50
     interchangeable
    0.47
     lurking
    0.46
    veis
    0.43
     flexible
    0.42
    lett
    0.42
    ös
    0.42
    alis
    0.41
     skall
    0.41
     teknik
    0.41
    Activations Density 0.001%

    No Known Activations