© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 21
    Prev
    Next
    INDEX
    Explanations

    on and with

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

    numbers, specific sequences, and code

    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_16k_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
     фундамента
    0.26
     &/
    0.23
     યોગ
    0.22
     および
    0.22
     iteratively
    0.22
     параметр
    0.22
     Weyl
    0.22
     алгорит
    0.21
     parametric
    0.21
     gyroscope
    0.21
    POSITIVE LOGITS
    s
    0.24
     imminent
    0.23
    last
    0.21
    hou
    0.20
     prosecution
    0.20
    ami
    0.20
    za
    0.20
    many
    0.20
    department
    0.20
    ro
    0.19
    Activations Density 0.001%

    No Known Activations