© 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. 125168
    Prev
    Next
    INDEX
    Explanations

    proxy statement

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

    course

    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
    лія
    0.48
    トレーニング
    0.45
    ですよ
    0.44
    Activate
    0.44
    /*
    0.44
    ATES
    0.44
     مید
    0.41
    尔
    0.41
    during
    0.41
    Engineering
    0.41
    POSITIVE LOGITS
     malonyl
    0.57
     diversifying
    0.51
     narcot
    0.51
     beaded
    0.50
     vegetarian
    0.48
     cylindrical
    0.48
     clonal
    0.48
     parab
    0.48
     divergent
    0.47
     methyl
    0.47
    Activations Density 0.001%

    No Known Activations