© 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. 129051
    Prev
    Next
    INDEX
    Explanations

    bass guitar or bassist

    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
     periodically
    -0.06
     additional
    -0.06
     ইতিমধ্যে
    -0.06
    ellate
    -0.05
    other
    -0.05
    ж
    -0.05
    现有
    -0.05
     ইতিমধ্যেই
    -0.05
     Other
    -0.05
     other
    -0.05
    POSITIVE LOGITS
     сопровожда
    0.07
     delicios
    0.07
     placent
    0.06
     nocturnal
    0.06
     фильма
    0.06
    unternehmen
    0.06
    ちゃんと
    0.06
    startDate
    0.06
     débil
    0.06
     когда
    0.06
    Activations Density 0.004%

    No Known Activations