© 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. 116238
    Prev
    Next
    INDEX
    Explanations

    seminal vesicle

    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
    さすが
    -0.06
    考虑到
    -0.06
     কীভাবে
    -0.06
     Thomson
    -0.06
     KN
    -0.06
     surprisingly
    -0.06
     paraît
    -0.06
    考えると
    -0.06
     Hou
    -0.06
     অস্বাভাবিক
    -0.06
    POSITIVE LOGITS
    8
    0.06
     applies
    0.06
     그녀
    0.06
     (=
    0.06
     모든
    0.06
     этого
    0.06
    ทุก
    0.06
     الانترنت
    0.06
     Applies
    0.05
    在这个
    0.05
    Activations Density 0.003%

    No Known Activations