© 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. 120217
    Prev
    Next
    INDEX
    Explanations

    icons or labels in UI elements

    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
     बजर
    -0.06
     लेते
    -0.06
     डाला
    -0.06
     соответствующие
    -0.06
    drill
    -0.06
     repost
    -0.06
     बिट
    -0.06
    相应的
    -0.05
    rung
    -0.05
     अदा
    -0.05
    POSITIVE LOGITS
    RAJ
    0.07
     forums
    0.06
    imah
    0.06
     både
    0.06
    主に
    0.06
     другому
    0.06
     இரண்டாம்
    0.06
    納期
    0.06
     جان
    0.06
    さまざまな
    0.06
    Activations Density 0.001%

    No Known Activations