© 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. 135025
    Prev
    Next
    INDEX
    Explanations

    reptiles tend, new smells, treatment can

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

    servers and performance

    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
     ratio
    0.51
     less
    0.50
    -
    0.50
     graphing
    0.50
     graph
    0.49
     most
    0.49
     quad
    0.49
     sai
    0.49
     Complement
    0.48
     quasi
    0.48
    POSITIVE LOGITS
    庥
    0.53
    GEBURTS
    0.52
    вовано
    0.50
    ylmethylsulfanyl
    0.48
    сколько
    0.46
     살펴보도록
    0.46
     지난해
    0.46
     станет
    0.46
     〢
    0.46
     산업
    0.46
    Activations Density 0.000%

    No Known Activations