© 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. 128293
    Prev
    Next
    INDEX
    Explanations

    film titles or names

    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
     अवधारणा
    -0.06
     underdog
    -0.06
    เฉพาะ
    -0.06
     Oklahoma
    -0.06
     男
    -0.05
     çeşit
    -0.05
     reason
    -0.05
     Rhonda
    -0.05
     women
    -0.05
    などの
    -0.05
    POSITIVE LOGITS
     euro
    0.06
     több
    0.06
     euros
    0.06
     काटकर
    0.06
     nicer
    0.06
    مسه
    0.06
     സഹായി
    0.06
     meticulously
    0.06
     staining
    0.06
     হত্যাকা
    0.06
    Activations Density 0.018%

    No Known Activations