© 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. 128700
    Prev
    Next
    INDEX
    Explanations

    Brain metastases

    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
    ),
    -0.08
    ],
    -0.07
     la
    -0.07
    `,
    -0.07
     The
    -0.07
     the
    -0.06
    】,
    -0.06
    ",
    -0.06
    ;,
    -0.06
     ),
    -0.06
    POSITIVE LOGITS
     просто
    0.08
     практически
    0.07
     очень
    0.07
     więc
    0.07
     весьма
    0.06
     все
    0.06
     nahezu
    0.06
    なのです
    0.06
     так
    0.06
    에서도
    0.06
    Activations Density 0.002%

    No Known Activations