© 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. 117298
    Prev
    Next
    INDEX
    Explanations

    UN/AP/OS/information/service/documents/content/records

    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
     in
    -0.08
     on
    -0.07
     sua
    -0.07
     أثناء
    -0.06
     with
    -0.06
     نظری
    -0.06
     during
    -0.06
    Those
    -0.06
     from
    -0.06
    कभी
    -0.06
    POSITIVE LOGITS
     அனுப்ப
    0.07
     früheren
    0.07
     notification
    0.07
    附件
    0.06
     you
    0.06
    名称
    0.06
     communiqué
    0.06
     sculptural
    0.06
     recent
    0.06
     direccion
    0.06
    Activations Density 0.002%

    No Known Activations