© 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. 129000
    Prev
    Next
    INDEX
    Explanations

    financial index change

    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
     に
    -0.07
     を
    -0.07
     stronger
    -0.06
    varepsilon
    -0.06
     sharper
    -0.06
     início
    -0.06
     eryth
    -0.06
     Messaging
    -0.06
     مام
    -0.05
     subsequent
    -0.05
    POSITIVE LOGITS
     bertanggung
    0.06
     പല
    0.06
    !"
    0.06
    ľ
    0.06
     განს
    0.06
    有好
    0.06
     buiten
    0.06
     tieto
    0.06
     tendencies
    0.06
    adjust
    0.06
    Activations Density 0.004%

    No Known Activations