© 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. 116415
    Prev
    Next
    INDEX
    Explanations

    response or answer

    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
    त्‍
    -0.06
     still
    -0.06
    basename
    -0.06
    ಣ್ಣ
    -0.06
     By
    -0.05
     описы
    -0.05
     তখনও
    -0.05
     بقى
    -0.05
     describe
    -0.05
     describing
    -0.05
    POSITIVE LOGITS
     réponse
    0.12
     response
    0.12
     respuesta
    0.11
     risposta
    0.11
    response
    0.11
     ответ
    0.11
     reply
    0.11
     resposta
    0.11
    Response
    0.11
     responses
    0.11
    Activations Density 0.049%

    No Known Activations