© 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. 116412
    Prev
    Next
    INDEX
    Explanations

    ();, db structure

    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
     другие
    -0.07
     other
    -0.07
     Vas
    -0.06
     diğer
    -0.06
    其他
    -0.06
     других
    -0.06
     fruitful
    -0.06
    其余
    -0.06
     orden
    -0.06
     altre
    -0.06
    POSITIVE LOGITS
     shouldn
    0.07
     skulle
    0.07
     désormais
    0.06
    Any
    0.06
     alongside
    0.06
    Also
    0.06
    Because
    0.06
     debería
    0.06
     descend
    0.06
     अवधारणा
    0.06
    Activations Density 0.006%

    No Known Activations