© 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. 129471
    Prev
    Next
    INDEX
    Explanations

    code blocks and programming syntax

    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
     og
    -0.06
    これらの
    -0.06
     این
    -0.06
    ;-
    -0.06
     ഈ
    -0.06
    藪
    -0.05
    ,),
    -0.05
    এই
    -0.05
    seem
    -0.05
    ,-
    -0.05
    POSITIVE LOGITS
     you
    0.08
     एक्टर
    0.08
     created
    0.07
     केल्यानंतर
    0.07
     ranging
    0.07
    వు
    0.06
    演员
    0.06
     experience
    0.06
     anguish
    0.06
     actors
    0.06
    Activations Density 0.003%

    No Known Activations