© 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. 228958
    Prev
    Next
    INDEX
    Explanations

    depolarized turkey processes

    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
    ணைய
    0.47
    私たちは
    0.45
     Федера
    0.45
    bordered
    0.45
    我们
    0.44
    如图
    0.44
    𒇉
    0.43
    rägen
    0.43
    landa
    0.43
    朗
    0.43
    POSITIVE LOGITS
    issement
    0.45
    omani
    0.45
     acceler
    0.41
     awarding
    0.40
     kejadian
    0.39
     exhaust
    0.39
    首次
    0.39
     motivic
    0.39
     Ic
    0.39
    ਹੀ
    0.39
    Activations Density 0.001%

    No Known Activations