© 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. 12504
    Prev
    Next
    INDEX
    Explanations

    describing sizes and dimensions

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

    performance best/better/less approximation

    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
     your
    0.43
     using
    0.43
     each
    0.42
     electrophoresis
    0.41
     waveguides
    0.40
     cylindrical
    0.39
     tuo
    0.39
    丶
    0.39
     transpired
    0.38
    deposited
    0.38
    POSITIVE LOGITS
     размеры
    0.61
     サイズ
    0.51
     Größen
    0.50
     Sizes
    0.48
     варианты
    0.46
     результат
    0.45
     sizes
    0.44
     pequeñas
    0.43
     cenderung
    0.43
    मुझे
    0.43
    Activations Density 0.000%

    No Known Activations