© 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. 119438
    Prev
    Next
    INDEX
    Explanations

    power, %, 3

    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
     здесь
    -0.07
     опять
    -0.06
     apps
    -0.06
     почти
    -0.06
     इसे
    -0.06
    是
    -0.06
     hampir
    -0.06
     જેને
    -0.06
     اسے
    -0.06
     niente
    -0.06
    POSITIVE LOGITS
     participate
    0.07
     their
    0.07
     NEW
    0.06
     enrich
    0.06
     cultivate
    0.06
     contribute
    0.06
     demonstrate
    0.06
     emergent
    0.06
     সিদ্ধান্ত
    0.06
     forefront
    0.06
    Activations Density 0.001%

    No Known Activations