© 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. 209363
    Prev
    Next
    INDEX
    Explanations

    desire for products plunged into wars reflecting changes

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

    within phrases

    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
    лил
    0.49
    ماس
    0.46
    意的
    0.44
    尽管
    0.43
    యన
    0.42
    喜
    0.42
    Titulo
    0.41
    र्जा
    0.41
    واصل
    0.41
    臧
    0.41
    POSITIVE LOGITS
     выйти
    0.50
     subtiliter
    0.48
    det
    0.48
     бара
    0.48
    ut
    0.47
    𝘀
    0.47
     シングル
    0.47
     および
    0.47
     ট্রেন
    0.46
    arai
    0.46
    Activations Density 0.000%

    No Known Activations