© 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. 117624
    Prev
    Next
    INDEX
    Explanations

    -

    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
     ফ্রি
    -0.07
     escritor
    -0.06
     homes
    -0.06
     Malays
    -0.06
    <h4>
    -0.06
    রাতে
    -0.06
    maktan
    -0.06
    рав
    -0.06
    кус
    -0.06
     Escola
    -0.06
    POSITIVE LOGITS
     sedangkan
    0.06
    ...?
    0.06
     cinch
    0.06
    履行
    0.06
     стой
    0.06
    inac
    0.06
     通常
    0.06
     quickest
    0.06
     granting
    0.06
     transmettre
    0.05
    Activations Density 0.146%

    No Known Activations