© 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. 119734
    Prev
    Next
    INDEX
    Explanations

    copyrights and service marks

    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
    一部分
    -0.07
     normally
    -0.07
     predetermined
    -0.06
     normalmente
    -0.06
     membros
    -0.06
     statistically
    -0.06
    normally
    -0.06
    比如说
    -0.06
     przez
    -0.06
     Vous
    -0.06
    POSITIVE LOGITS
    Service
    0.06
     trademarks
    0.06
     service
    0.06
    ницы
    0.06
     decade
    0.05
     remarkable
    0.05
    ervice
    0.05
    olato
    0.05
    And
    0.05
     strong
    0.05
    Activations Density 0.009%

    No Known Activations