© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6512
    Prev
    Next
    INDEX
    Explanations

    together with

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

    explaining complexity and contingency

    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_53_width_65k_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
    rances
    0.40
    यंस
    0.39
    шли
    0.38
    ினா
    0.38
    ',{
    0.38
     страда
    0.36
    Roe
    0.36
    CONFIGURATION
    0.36
    sce
    0.36
    рованы
    0.36
    POSITIVE LOGITS
    essen
    0.42
     ZA
    0.41
     sorta
    0.39
     ܘ
    0.38
    orgetown
    0.38
     thermally
    0.38
    ípio
    0.37
     supervise
    0.37
     ইস্ট
    0.37
     cilt
    0.37
    Activations Density 0.002%

    No Known Activations