© 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-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 128932
    Prev
    Next
    INDEX
    Explanations

    lists and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     firstly
    -0.07
     επίσης
    -0.06
     umożliw
    -0.06
    ですよ
    -0.06
     позволит
    -0.06
     большинстве
    -0.05
    Firstly
    -0.05
    .[/
    -0.05
     ermöglicht
    -0.05
    এছ
    -0.05
    POSITIVE LOGITS
     when
    0.07
     with
    0.06
     घोटा
    0.06
     where
    0.06
    ところで
    0.06
     Noetherian
    0.06
     taxing
    0.06
     hewan
    0.06
     který
    0.05
     दहा
    0.05
    Activations Density 0.001%

    No Known Activations