© 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. 120571
    Prev
    Next
    INDEX
    Explanations

    html tags and attributes

    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
     करके
    -0.07
     kinda
    -0.06
     ৪র্থ
    -0.06
    代わりに
    -0.06
    ayısıyla
    -0.06
     비슷
    -0.06
     suggests
    -0.06
     ৯ম
    -0.05
    反而
    -0.05
    ែម
    -0.05
    POSITIVE LOGITS
    如果
    0.06
    ন্ড
    0.06
     Drummond
    0.06
    严格
    0.06
     predominantly
    0.06
     invertebrates
    0.06
     cakes
    0.06
     específicamente
    0.06
    خصوص
    0.06
     běž
    0.06
    Activations Density 0.039%

    No Known Activations