© 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. 120079
    Prev
    Next
    INDEX
    Explanations

    input field 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
    ennzeichnet
    -0.07
     podnik
    -0.06
     subversive
    -0.06
    strict
    -0.06
     austere
    -0.06
    <0xAF>
    -0.06
    Ĭ
    -0.05
     után
    -0.05
    ERCIAL
    -0.05
    ുകയും
    -0.05
    POSITIVE LOGITS
     একান্ত
    0.07
     Ikat
    0.06
    翩
    0.06
     old
    0.06
     hérit
    0.06
     طریق
    0.06
     सब्जी
    0.05
     نیز
    0.05
    labyrinth
    0.05
    कन्या
    0.05
    Activations Density 0.002%

    No Known Activations