© 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. 117101
    Prev
    Next
    INDEX
    Explanations

    dates from to

    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
    :
    -0.07
     ঃ
    -0.07
    ár
    -0.06
     but
    -0.06
    ;
    -0.06
    ocentric
    -0.06
    燾
    -0.06
    Hell
    -0.06
     selon
    -0.05
     Extras
    -0.05
    POSITIVE LOGITS
     детали
    0.06
    ക്കുകയും
    0.06
     அந்த
    0.06
    用户
    0.06
     пользователь
    0.06
     아무
    0.06
     takiej
    0.06
     thoſe
    0.06
     anyone
    0.06
     anybody
    0.06
    Activations Density 0.008%

    No Known Activations