© 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. 119944
    Prev
    Next
    INDEX
    Explanations

    starts of sentences

    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
    ंपूर्वी
    -0.06
     danos
    -0.06
    ․
    -0.06
     многое
    -0.06
     लक्षण
    -0.06
    াযোগ
    -0.06
    杞
    -0.06
     cần
    -0.06
     incumbents
    -0.06
     ['(?
    -0.05
    POSITIVE LOGITS
     också
    0.06
     invade
    0.06
    <0xBC>
    0.06
    ~!
    0.06
     también
    0.06
     उठाते
    0.06
     సౌ
    0.05
     AGAIN
    0.05
    บูร
    0.05
     BIN
    0.05
    Activations Density 0.001%

    No Known Activations