© 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. 128554
    Prev
    Next
    INDEX
    Explanations

    Invictus Games

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

    example pattern

    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
     certos
    0.45
     tots
    0.45
    ト
    0.45
    ನ್
    0.43
    ד
    0.42
     уто
    0.42
     κον
    0.42
     bullion
    0.41
    動
    0.41
     appris
    0.41
    POSITIVE LOGITS
     Για
    0.49
     对于
    0.47
     Determining
    0.45
    ຜະລິດຕ
    0.45
     Tại
    0.45
     শত্রু
    0.44
    报考
    0.44
     Для
    0.43
    required
    0.43
     Required
    0.43
    Activations Density 0.001%

    No Known Activations