© 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. 128826
    Prev
    Next
    INDEX
    Explanations

    azure cloud services

    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
    :
    -0.07
     permanent
    -0.06
    Init
    -0.06
     করায়
    -0.06
     выну
    -0.05
    は
    -0.05
    :'
    -0.05
     Dund
    -0.05
    :"+
    -0.05
    permanent
    -0.05
    POSITIVE LOGITS
     مجموعة
    0.06
     entsprechenden
    0.06
     defamatory
    0.06
     જોવા
    0.06
     participaron
    0.06
     espiritual
    0.06
    หลากหลาย
    0.06
     Notion
    0.06
     Daher
    0.06
    າມ
    0.06
    Activations Density 0.011%

    No Known Activations