© 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. 10356
    Prev
    Next
    INDEX
    Explanations

    infinite possibilities and quantities

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

    infinite, unlimited, endless

    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
     образа
    0.58
    뗀
    0.56
    욌
    0.56
     acides
    0.54
     eased
    0.52
    тинен
    0.50
    ⿹
    0.49
    kBtu
    0.49
     eases
    0.49
    ἲ
    0.49
    POSITIVE LOGITS
     infinite
    1.55
     Infinite
    1.45
    無限
    1.43
    infinite
    1.38
    无限
    1.36
     unlimited
    1.30
    Infinite
    1.30
     infinito
    1.29
     infinity
    1.28
     infinitely
    1.27
    Activations Density 0.070%

    No Known Activations